INDEX

Explanations

phrases related to direct confrontation or close interactions

oai_token-act-pair · gpt-3.5-turbo

phrases related to proximity or closeness

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ypes

-0.75

urable

-0.74

ĨĴ

-0.69

iates

-0.69

atile

-0.66

ATIONS

-0.66

states

-0.65

codes

-0.65

ŃĶ

-0.63

cooked

-0.61

POSITIVE LOGITS

toe

1.13

 heel

0.98

 heels

0.91

 glove

0.88

 mouth

0.86

 shoulder

0.84

 nose

0.83

 foot

0.82

toe

0.79

 chin

0.79

Activations Density 0.069%

phrases related to direct confrontation or close interactions

phrases related to proximity or closeness

No Comments

No Known Activations