INDEX

Explanations

proper nouns starting with the letter "I" followed by an "s" and ending with another word

oai_token-act-pair · gpt-3.5-turbo

interrogative statements beginning with "Is."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 kicker

-0.68

 deal

-0.64

 Bowser

-0.62

 purse

-0.61

 ticket

-0.61

 straight

-0.60

 whip

-0.59

 credit

-0.58

 similar

-0.58

strous

-0.58

POSITIVE LOGITS

Is

3.70

Was

1.78

Does

1.77

Isn

1.76

Is

1.75

Are

1.74

Has

1.73

Es

1.57

Can

1.56

Os

1.53

Activations Density 0.010%

proper nouns starting with the letter "I" followed by an "s" and ending with another word

interrogative statements beginning with "Is."

No Comments

No Known Activations