INDEX

Explanations

phrases referring to something being popular or controversial

oai_token-act-pair · gpt-3.5-turbo

the term "hot" used in various contexts

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

ufact

-0.95

uther

-0.79

ajor

-0.76

 confir

-0.75

ĸļ

-0.73

eca

-0.73

atively

-0.73

ARDIS

-0.71

yss

-0.70

INAL

-0.69

POSITIVE LOGITS

 spots

0.92

ness

0.89

ened

0.87

 Chili

0.87

hot

0.87

headed

0.86

Spot

0.85

 stove

0.84

 hotter

0.84

shots

0.83

Activations Density 0.020%

phrases referring to something being popular or controversial

the term "hot" used in various contexts

No Comments

No Known Activations