INDEX

Explanations

references to specific countries and organizations, particularly focusing on financial transactions and government agencies

oai_token-act-pair · gpt-3.5-turbo

names of countries and regions, particularly those involved in international contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

plet

-0.78

vana

-0.69

 havoc

-0.68

minded

-0.66

wagon

-0.65

psy

-0.64

 glim

-0.63

aciously

-0.62

bread

-0.61

chall

-0.59

POSITIVE LOGITS

;;;;;;;;;;;;

0.88

 Association

0.83

 Robotics

0.67

LLP

0.67

 fame

0.65

 Foundation

0.65

 Instruction

0.65

 Devices

0.65

 Volunteers

0.65

 Accountability

0.63

Activations Density 0.133%

references to specific countries and organizations, particularly focusing on financial transactions and government agencies

names of countries and regions, particularly those involved in international contexts

No Comments

No Known Activations