INDEX

Explanations

instances of verbs with 'bel-' as a prefix

oai_token-act-pair · gpt-3.5-turbo

instances of the word "belittle" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

inals

-0.81

office

-0.80

hibition

-0.78

anwhile

-0.76

 Regulation

-0.74

INAL

-0.73

 Enhancement

-0.71

 Fields

-0.70

azines

-0.70

iety

-0.69

POSITIVE LOGITS

bel

0.90

ittle

0.88

ieving

0.83

gian

0.78

ongs

0.77

phe

0.76

aying

0.76

ayer

0.75

ounge

0.73

ayed

0.73

Activations Density 0.006%

instances of verbs with 'bel-' as a prefix

instances of the word "belittle" and its variations

No Comments

No Known Activations