INDEX

Explanations

phrases related to attributing actions or characteristics to specific individuals

oai_token-act-pair · gpt-3.5-turbo

the verb "was" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 depression

-0.69

 sucker

-0.68

 predatory

-0.67

Ber

-0.63

 Highlands

-0.63

 prosecuting

-0.62

upt

-0.62

 rehab

-0.62

 scalp

-0.61

 biting

-0.61

POSITIVE LOGITS

DragonMagazine

1.15

bsite

1.02

theless

1.00

ques

0.97

que

0.93

tesy

0.92

swick

0.92

flo

0.91

was

0.89

BuyableInstoreAndOnline

0.89

Activations Density 0.016%

phrases related to attributing actions or characteristics to specific individuals

the verb "was" in various contexts

No Comments

No Known Activations