INDEX

Explanations

mentions of political and governmental entities or activities

oai_token-act-pair · gpt-3.5-turbo

references to various political and societal entities and their actions

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

ãĥ¥

-0.71

aughter

-0.66

anya

-0.62

REE

-0.56

enture

-0.56

[];

-0.56

ety

-0.55

atching

-0.55

rating

-0.55

ocalypse

-0.55

POSITIVE LOGITS

 alas

0.88

 albeit

0.84

 meanwhile

0.81

 namely

0.78

ItemThumbnailImage

0.76

 unsurprisingly

0.74

 however

0.73

huh

0.73

 sensing

0.73

aka

0.72

Activations Density 0.345%

mentions of political and governmental entities or activities

references to various political and societal entities and their actions

No Comments

No Known Activations