INDEX

Explanations

words related to a kitchen or kitchen-related activities

oai_token-act-pair · gpt-3.5-turbo

references to kitchens and related home spaces

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

Reviewer

-0.80

 Trooper

-0.76

utic

-0.74

ignty

-0.72

idas

-0.72

inates

-0.72

ullah

-0.69

ioxide

-0.69

vernment

-0.68

reon

-0.67

POSITIVE LOGITS

 appliances

1.00

 appliance

0.98

 cabinets

0.93

 sink

0.89

 remod

0.88

Aid

0.87

ette

0.84

ware

0.82

maid

0.82

washer

0.82

Activations Density 0.048%

words related to a kitchen or kitchen-related activities

references to kitchens and related home spaces

No Comments

No Known Activations