INDEX

Explanations

proper nouns related to people or places

oai_token-act-pair · gpt-3.5-turbo

references to notable figures and their actions or qualities 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

)]

-0.72

Ire

-0.68

bilt

-0.64

)-

-0.64

ramid

-0.63

 Leban

-0.62

sembly

-0.62

ilater

-0.62

ciplinary

-0.62

nesota

-0.61

POSITIVE LOGITS

 goddamn

0.86

 ______

0.82

!".

0.80

.ãĢį

0.71

 fucking

0.68

 godd

0.65

};

0.64

?".

0.63

 damn

0.63

tumblr

0.61

Activations Density 0.837%

proper nouns related to people or places

references to notable figures and their actions or qualities in various contexts

No Comments

No Known Activations