INDEX

Explanations

links prompting the reader to access additional information or sources

oai_token-act-pair · gpt-3.5-turbo

verbs related to reading and viewing content

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

Lenin

-0.68

iazep

-0.64

rang

-0.63

ĸļ

-0.63

angled

-0.62

BuyableInstoreAndOnline

-0.62

inals

-0.61

ablishment

-0.60

rays

-0.60

entric

-0.59

POSITIVE LOGITS

 yourself

0.86

 yourselves

0.84

SOURCE

0.79

 yours

0.76

 Attribution

0.73

 HERE

0.72

owan

0.71

idas

0.67

 your

0.67

NEWS

0.64

Activations Density 0.101%

links prompting the reader to access additional information or sources

verbs related to reading and viewing content

No Comments

No Known Activations