INDEX

Explanations

phrases enclosed in quotation marks often related to specific texts or contexts

oai_token-act-pair · gpt-3.5-turbo

the presence of parentheses indicating quoted material or dialogue

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

orate

-0.76

 Federation

-0.66

 retali

-0.63

RC

-0.62

 cooker

-0.62

 stalk

-0.61

 brushes

-0.60

usters

-0.59

 Seaf

-0.59

 Hodg

-0.59

POSITIVE LOGITS

catentry

0.98

wcsstore

0.88

iquid

0.81

Hello

0.81

["

0.76

SELECT

0.75

onduct

0.75

iHUD

0.74

mund

0.73

hey

0.73

Activations Density 0.014%

phrases enclosed in quotation marks often related to specific texts or contexts

the presence of parentheses indicating quoted material or dialogue

No Comments

No Known Activations