INDEX

Explanations

references to statements or thoughts from others

oai_token-act-pair · gpt-3.5-turbo

instances 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

eem

-0.71

etting

-0.65

typ

-0.63

dc

-0.60

arter

-0.58

housing

-0.58

 Pair

-0.58

ourgeois

-0.57

OOL

-0.57

 behold

-0.57

POSITIVE LOGITS

 been

1.51

been

1.31

 undergone

1.12

 Been

1.09

 become

1.07

 gotten

1.05

 begun

1.03

 gone

0.97

 arisen

0.96

 risen

0.95

Activations Density 0.279%

references to statements or thoughts from others

instances of the word "have."

No Comments

No Known Activations