INDEX

Explanations

proper nouns related to individuals and their roles or performances

oai_token-act-pair · gpt-3.5-turbo

phrases indicating continuous actions or states related to performance

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Feminist

-0.73

 reviewer

-0.70

 Orwell

-0.69

Jou

-0.68

 bureaucr

-0.68

 censor

-0.66

 Apart

-0.66

microsoft

-0.65

 Lauder

-0.65

 Capitalism

-0.65

POSITIVE LOGITS

 preseason

0.95

 teammates

0.91

 batted

0.88

 bounced

0.88

 undrafted

0.87

Coach

0.86

cussion

0.85

 teammate

0.84

 coached

0.83

juries

0.83

Activations Density 0.356%

proper nouns related to individuals and their roles or performances

phrases indicating continuous actions or states related to performance

No Comments

No Known Activations