INDEX

Explanations

phrases indicating a particular proposition or statement

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "that" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

RIP

-0.58

 Bombay

-0.56

 downs

-0.53

 Osiris

-0.53

ron

-0.53

Luck

-0.51

Cay

-0.50

 That

-0.50

 Legend

-0.50

Boss

-0.50

POSITIVE LOGITS

 resulted

0.81

iago

0.76

 fateful

0.75

 mattered

0.75

 culminated

0.74

 arose

0.73

soever

0.72

chers

0.71

 occurred

0.70

 amounted

0.69

Activations Density 0.524%

phrases indicating a particular proposition or statement

occurrences of the word "that" in various contexts

No Comments

No Known Activations