INDEX

Explanations

instances where the text mentions trying to achieve a certain quality or characteristic

oai_token-act-pair · gpt-3.5-turbo

instances of the word "be" used 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 impossibility

-0.73

 mandate

-0.69

 fray

-0.66

 woes

-0.65

 request

-0.65

 demographics

-0.64

 Struggle

-0.63

 attempt

-0.63

 Times

-0.63

 struggle

-0.61

POSITIVE LOGITS

 able

1.14

league

0.99

leeve

0.93

fits

0.91

 judged

0.89

acons

0.88

witch

0.87

 aware

0.87

friends

0.87

amed

0.85

Activations Density 0.165%

instances where the text mentions trying to achieve a certain quality or characteristic

instances of the word "be" used in various contexts

No Comments

No Known Activations