INDEX

Explanations

phrases or words related to high temperature or intense activity

oai_token-act-pair · gpt-3.5-turbo

instances of the word "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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ufact

-0.91

ajor

-0.79

uther

-0.78

eca

-0.78

INAL

-0.73

atively

-0.72

ARDIS

-0.71

 confir

-0.70

yss

-0.69

vous

-0.68

POSITIVE LOGITS

 spots

0.91

 Chili

0.89

ness

0.86

 stove

0.86

headed

0.85

 hotter

0.84

hot

0.83

dogs

0.83

 potato

0.83

 sauce

0.82

Activations Density 0.021%

phrases or words related to high temperature or intense activity

instances of the word "hot" used in various contexts

No Comments

No Known Activations