INDEX

Explanations

numerical references and measurements

oai_token-act-pair · gpt-3.5-turbo

specific numerical data or references to dates and measurements

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

 Masquerade

-0.67

 Ridley

-0.66

ADRA

-0.64

abase

-0.61

 Foss

-0.60

Fei

-0.59

 Ashes

-0.58

 Triangle

-0.57

yles

-0.56

 guiActiveUnfocused

-0.56

POSITIVE LOGITS

monary

0.77

acan

0.75

0.71

warts

0.68

clinton

0.65

0.64

Activations Density 0.157%

numerical references and measurements

specific numerical data or references to dates and measurements

No Comments

No Known Activations