INDEX

Explanations

phrases indicating explanation or justification

oai_token-act-pair · gpt-3.5-turbo

expressions indicating justification or explanation

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

Blue

-0.62

Dragon

-0.60

ModLoader

-0.60

TR

-0.59

rab

-0.58

Enough

-0.57

cause

-0.57

Tokens

-0.57

 procedural

-0.55

VERSION

-0.55

POSITIVE LOGITS

SPONSORED

0.75

 alone

0.72

å£«

0.71

idents

0.66

phas

0.65

zik

0.63

we

0.60

gha

0.60

akedown

0.59

 contrasts

0.59

Activations Density 0.080%

phrases indicating explanation or justification

expressions indicating justification or explanation

No Comments

No Known Activations