INDEX

Explanations

phrases related to thoroughness or detailed investigations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating comprehensiveness or careful examination

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

AIN

-0.71

 Tonight

-0.68

 Rebels

-0.68

qqa

-0.66

dust

-0.64

nesota

-0.62

birds

-0.62

CHAT

-0.62

agne

-0.61

ospels

-0.61

POSITIVE LOGITS

bred

1.40

fare

1.04

ness

0.99

going

0.94

 thorough

0.93

 examination

0.84

 examinations

0.80

spection

0.79

done

0.76

spect

0.75

Activations Density 0.022%

phrases related to thoroughness or detailed investigations

phrases indicating comprehensiveness or careful examination

No Comments

No Known Activations