INDEX

Explanations

the beginning of sentences

oai_token-act-pair · gpt-3.5-turbo

the indefinite article "a" and its variants, indicating its focus on the presence of singular nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

geist

-0.66

Own

-0.66

iffs

-0.65

bugs

-0.63

otte

-0.63

ioch

-0.62

mie

-0.62

 Runs

-0.61

oad

-0.61

 Teams

-0.61

POSITIVE LOGITS

 spokeswoman

0.97

 testament

0.96

 hallmark

0.94

rouse

0.94

 spokesman

0.92

 precursor

0.90

 statement

0.90

 euphem

0.88

hem

0.87

 spokesperson

0.87

Activations Density 0.172%

the beginning of sentences

the indefinite article "a" and its variants, indicating its focus on the presence of singular nouns

No Comments

No Known Activations