INDEX

Explanations

words related to meals and dining experiences

oai_token-act-pair · gpt-3.5-turbo

references to meals

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ignty

-0.73

idency

-0.72

vernment

-0.66

 governmental

-0.65

orate

-0.63

 Morse

-0.61

inates

-0.60

orporated

-0.59

ioxide

-0.59

hips

-0.59

POSITIVE LOGITS

 meal

1.28

worms

1.24

 meals

1.18

 Meal

1.13

 eaten

0.96

worm

0.94

 buffet

0.90

 breakfast

0.83

 foods

0.82

 eater

0.82

Activations Density 0.011%

words related to meals and dining experiences

references to meals

No Comments

No Known Activations