INDEX

Explanations

phrases related to standard or typical operations or conditions

oai_token-act-pair · gpt-3.5-turbo

terms related to conventional norms and standards

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

psey

-0.76

ificantly

-0.73

amia

-0.72

untarily

-0.70

orously

-0.68

initely

-0.65

asca

-0.64

zilla

-0.63

leased

-0.63

antically

-0.62

POSITIVE LOGITS

 fare

0.95

 greeting

0.89

 decency

0.82

 procedure

0.74

 Occupations

0.72

 tropes

0.70

ItemImage

0.68

iquette

0.67

hello

0.66

ensical

0.66

Activations Density 0.474%

phrases related to standard or typical operations or conditions

terms related to conventional norms and standards

No Comments

No Known Activations