INDEX

Explanations

references to places or things involving the word "strip"

oai_token-act-pair · gpt-3.5-turbo

references to "strip" locations, particularly in urban or entertainment contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

pheus

-0.76

 Aval

-0.76

rious

-0.75

é¾įå

-0.75

Cao

-0.75

VERTIS

-0.72

hran

-0.71

lished

-0.71

ä

-0.69

å§«

-0.68

POSITIVE LOGITS

 malls

1.16

 strip

1.12

strip

1.03

isode

0.89

 strips

0.86

 mall

0.86

aways

0.84

 stripping

0.83

 Strip

0.82

isal

0.80

Activations Density 0.008%

references to places or things involving the word "strip"

references to "strip" locations, particularly in urban or entertainment contexts

No Comments

No Known Activations