INDEX

Explanations

phrases indicating setting or location

oai_token-act-pair · gpt-3.5-turbo

phrases indicating scheduled events or releases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Pastebin

-0.62

luence

-0.61

alez

-0.60

orean

-0.59

loo

-0.59

ocations

-0.57

 mathemat

-0.55

illian

-0.55

udeau

-0.55

POSITIVE LOGITS

tle

1.06

abl

1.01

 aside

0.90

 sail

0.90

 forth

0.87

ters

0.85

tering

0.83

worms

0.83

upt

0.81

list

0.80

Activations Density 0.034%

phrases indicating setting or location

phrases indicating scheduled events or releases

No Comments

No Known Activations