INDEX

Explanations

names of people and places

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names and places

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

psey

-0.78

putable

-0.73

agine

-0.71

 sensing

-0.70

 Claire

-0.70

inarily

-0.69

Fas

-0.67

anamo

-0.66

uden

-0.66

initions

-0.66

POSITIVE LOGITS

aval

0.81

Discuss

0.76

eful

0.71

****************

0.71

 Dharma

0.69

********************************

0.69

Lot

0.68

abal

0.68

LLOW

0.67

esville

0.67

Activations Density 0.048%

names of people and places

mentions of specific names and places

No Comments

No Known Activations