INDEX

Explanations

mentions of specific locations such as streets or buildings

oai_token-act-pair · gpt-3.5-turbo

specific location names or terms related to addressing places

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

advertising

-0.89

 fulfillment

-0.72

uations

-0.64

bats

-0.63

miss

-0.62

iosyncr

-0.61

ento

-0.60

utations

-0.59

gem

-0.59

sson

-0.58

POSITIVE LOGITS

EStream

0.83

xual

0.71

xon

0.69

é¾

0.66

 gradient

0.64

âĪĴ

0.63

ALT

0.62

spir

0.60

assic

0.59

 Sheridan

0.57

Activations Density 0.293%

mentions of specific locations such as streets or buildings

specific location names or terms related to addressing places

No Comments

No Known Activations