INDEX

Explanations

mentions of food or dining-related words

oai_token-act-pair · gpt-3.5-turbo

words related to food, specifically types or categories of food

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ness

-0.87

nesses

-0.78

dale

-0.76

endon

-0.75

igans

-0.74

sung

-0.72

ged

-0.72

aine

-0.70

ened

-0.68

ingen

-0.68

POSITIVE LOGITS

chnology

1.19

llular

1.02

rers

0.89

ctic

0.78

anu

0.76

lli

0.74

lled

0.71

 nucleus

0.70

cki

0.70

ptive

0.66

Activations Density 0.128%

mentions of food or dining-related words

words related to food, specifically types or categories of food

No Comments

No Known Activations