INDEX

Explanations

timestamps relative to movement or physical activity

oai_token-act-pair · gpt-3.5-turbo

various forms of the word "movement."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

zona

-0.72

ihil

-0.72

zan

-0.68

unts

-0.68

oys

-0.66

nect

-0.66

GE

-0.65

ãĤ©

-0.65

odium

-0.63

ju

-0.62

POSITIVE LOGITS

 movements

0.93

 movement

0.90

 motions

0.86

peed

0.82

letal

0.75

able

0.75

 motion

0.73

 disorder

0.73

 direction

0.72

 sickness

0.72

Activations Density 0.040%

timestamps relative to movement or physical activity

various forms of the word "movement."

No Comments

No Known Activations