INDEX

Explanations

references to violent actions or events involving law enforcement

oai_token-act-pair · gpt-3.5-turbo

articles and demonstratives preceding nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

!/

-0.77

Contents

-0.76

ATURES

-0.75

 Izan

-0.74

Æ

-0.73

[/

-0.72

/-

-0.70

 Releases

-0.69

 Languages

-0.69

Allow

-0.69

POSITIVE LOGITS

rouse

1.06

 woman

1.05

 handful

0.98

 couple

0.97

 burglary

0.91

 colleague

0.89

lot

0.89

 multitude

0.88

 small

0.87

 funeral

0.87

Activations Density 0.695%

references to violent actions or events involving law enforcement

articles and demonstratives preceding nouns

No Comments

No Known Activations