INDEX

Explanations

negative statements or criticisms

oai_token-act-pair · gpt-3.5-turbo

negative constructions or expressions of inability

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

rys

-0.71

ription

-0.71

 IMAGES

-0.69

afort

-0.66

elist

-0.66

endix

-0.66

cius

-0.65

andan

-0.65

pora

-0.64

rimination

-0.64

POSITIVE LOGITS

íķ

0.73

 darn

0.72

Availability

0.70

ifiable

0.69

èª

0.68

Õ

0.68

WHERE

0.68

Fuck

0.63

 Pradesh

0.63

 bothered

0.63

Activations Density 0.091%

negative statements or criticisms

negative constructions or expressions of inability

No Comments

No Known Activations