INDEX

Explanations

phrases related to clothing and/or personal belongings

oai_token-act-pair · gpt-3.5-turbo

references to specific names or terms related to characters, authors, and objects

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

ammy

-0.74

 Seym

-0.71

icipated

-0.70

yers

-0.66

alm

-0.66

 acad

-0.63

illions

-0.62

illion

-0.62

 accur

-0.62

 latt

-0.62

POSITIVE LOGITS

nuts

0.86

uates

0.85

uated

0.82

itably

0.78

FORE

0.76

owship

0.75

pole

0.73

velength

0.73

ttle

0.72

ters

0.72

Activations Density 0.110%

phrases related to clothing and/or personal belongings

references to specific names or terms related to characters, authors, and objects

No Comments

No Known Activations