INDEX

Explanations

words related to movement and location

oai_token-act-pair · gpt-3.5-turbo

locations and pathways in a setting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

-0.85

anson

-0.73

ighth

-0.69

anol

-0.68

olitics

-0.66

thood

-0.65

ourke

-0.65

phabet

-0.65

laus

-0.65

aned

-0.63

POSITIVE LOGITS

 bushes

0.91

 doorway

0.86

 courtyard

0.86

 ceiling

0.86

tyard

0.82

 nearest

0.78

 balcony

0.78

frame

0.78

wip

0.78

âĶĢâĶĢ

0.77

Activations Density 0.222%

words related to movement and location

locations and pathways in a setting

No Comments

No Known Activations