INDEX

Explanations

captions or text related to images or photos

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to captions and memes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

dinand

-0.73

estones

-0.69

olesterol

-0.68

 Jakarta

-0.66

usalem

-0.65

itaire

-0.65

 Skydragon

-0.65

 Transactions

-0.64

assium

-0.63

 Lumpur

-0.61

POSITIVE LOGITS

xual

0.98

ed

0.89

forth

0.86

 Leilan

0.77

edly

0.77

igans

0.74

anza

0.74

ual

0.73

ery

0.71

ing

0.71

Activations Density 0.048%

captions or text related to images or photos

terms and phrases related to captions and memes

No Comments

No Known Activations