INDEX

Explanations

instances of the word "have"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "have"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

catentry

-0.65

 Apart

-0.57

ocol

-0.55

 territ

-0.50

 fireball

-0.50

 colonization

-0.48

 neigh

-0.48

 smear

-0.48

osa

-0.47

 persuasion

-0.47

POSITIVE LOGITS

 been

1.19

been

1.02

 Been

0.92

 undergone

0.91

 gotten

0.89

 gone

0.83

 taken

0.81

 done

0.81

gotten

0.80

 begun

0.79

Activations Density 0.435%

instances of the word "have"

occurrences of the word "have"

No Comments

No Known Activations