INDEX

Explanations

Japanese names emphasized through italicization

oai_token-act-pair · gpt-3.5-turbo

names of individuals, particularly those associated with film or media

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

ccording

-0.74

 necessities

-0.62

 differed

-0.61

 entails

-0.60

 unfavorable

-0.60

 suppose

-0.59

Reviewer

-0.59

Asia

-0.59

PASS

-0.58

actionDate

-0.58

POSITIVE LOGITS

Jr

1.33

hetti

1.00

III

0.95

JR

0.93

kson

0.90

Sr

0.90

hoff

0.89

elli

0.88

otti

0.87

meier

0.87

Activations Density 0.209%

Japanese names emphasized through italicization

names of individuals, particularly those associated with film or media

No Comments

No Known Activations