INDEX

Explanations

phrases indicating distance or comparison between situations or objects

oai_token-act-pair · gpt-3.5-turbo

phrases expressing a degree of inadequacy or deficiency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ayne

-0.77

hiba

-0.77

assian

-0.75

alys

-0.72

yrs

-0.71

KA

-0.71

 sqor

-0.70

 Citation

-0.69

endez

-0.68

queue

-0.68

POSITIVE LOGITS

 infall

0.98

 flawless

0.98

 conclusive

0.95

 glamorous

0.92

 pristine

0.91

 insignificant

0.90

 frivolous

0.90

 conducive

0.90

 perfect

0.89

 exhaustive

0.88

Activations Density 0.073%

phrases indicating distance or comparison between situations or objects

phrases expressing a degree of inadequacy or deficiency

No Comments

No Known Activations