INDEX

Explanations

text related to opinions or statements made in a public or professional setting

oai_token-act-pair · gpt-3.5-turbo

negative or contradictory statements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ugal

-0.87

emetery

-0.80

illion

-0.77

Higher

-0.74

EMBER

-0.73

illions

-0.73

OTAL

-0.73

acebook

-0.71

 millenn

-0.70

uilt

-0.68

POSITIVE LOGITS

henko

0.71

 Tsarnaev

0.69

 herself

0.64

 adamant

0.63

 Mush

0.62

 rhet

0.62

Sud

0.61

 quoted

0.60

 schizophrenia

0.60

 himself

0.59

Activations Density 0.648%

text related to opinions or statements made in a public or professional setting

negative or contradictory statements

No Comments

No Known Activations