INDEX

Explanations

statements related to permissions or restrictions

oai_token-act-pair · gpt-3.5-turbo

sequences of text that are empty or contain no relevant content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Vaugh

-0.67

 Niet

-0.66

 Godd

-0.64

Byr

-0.64

 Brus

-0.63

 Bravo

-0.62

esides

-0.61

 Strauss

-0.61

Gaw

-0.60

 Barney

-0.59

POSITIVE LOGITS

Â¶

0.78

 optionally

0.72

 embodiments

0.67

 specified

0.67

][

0.67

 interval

0.66

 integer

0.65

obyl

0.64

 dynamically

0.64

ersive

0.64

Activations Density 0.737%

statements related to permissions or restrictions

sequences of text that are empty or contain no relevant content

No Comments

No Known Activations