INDEX

Explanations

terms related to laws, regulations, and political strategies

oai_token-act-pair · gpt-3.5-turbo

terms related to charges or accusations

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

iasis

-0.72

¬¼

-0.70

mberg

-0.62

 Assass

-0.59

xtap

-0.59

avin

-0.59

hou

-0.59

xton

-0.59

heng

-0.59

tiny

-0.58

POSITIVE LOGITS

 than

1.84

than

1.83

 Than

1.28

 harsher

0.76

 wiser

0.71

 Tradable

0.69

":"/

0.65

 nearer

0.64

"}],"

0.64

 quieter

0.62

Activations Density 0.884%

terms related to laws, regulations, and political strategies

terms related to charges or accusations

No Comments

No Known Activations