INDEX

Explanations

mentions of the word "Bra" with varying levels of specificity and relevance

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Bra."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ership

-0.81

matic

-0.79

regor

-0.75

ancial

-0.75

eers

-0.72

ARY

-0.72

omez

-0.71

 Gutenberg

-0.69

ovych

-0.69

TY

-0.69

POSITIVE LOGITS

ille

1.04

kes

0.92

hma

0.92

ided

0.85

Bra

0.84

ves

0.84

keley

0.84

illard

0.82

zz

0.81

very

0.81

Activations Density 0.008%

mentions of the word "Bra" with varying levels of specificity and relevance

occurrences of the term "Bra."

No Comments

No Known Activations