INDEX

Explanations

instances of the word "have"

oai_token-act-pair · gpt-3.5-turbo

the repetition 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

oshi

-0.68

catentry

-0.66

 Apart

-0.61

icking

-0.59

oji

-0.59

eem

-0.57

weed

-0.57

etting

-0.56

cus

-0.56

 bribe

-0.55

POSITIVE LOGITS

 been

1.28

been

1.03

 Been

0.92

 seen

0.92

 gotten

0.91

 begun

0.88

 become

0.86

 undergone

0.82

 done

0.80

 gone

0.79

Activations Density 0.258%

instances of the word "have"

the repetition of the word "have."

No Comments

No Known Activations