INDEX

Explanations

references to legal proceedings or events involving hearings

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "hearing" 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 @ 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

jac

-0.82

ecd

-0.72

rave

-0.70

football

-0.68

acea

-0.68

spr

-0.66

vier

-0.65

 Haram

-0.65

mson

-0.64

ienne

-0.64

POSITIVE LOGITS

 hearings

1.12

 transcripts

1.03

 examiner

0.99

 testimony

0.98

 proceedings

0.92

 convened

0.90

imony

0.87

 transcript

0.85

 hearing

0.83

 Hearing

0.83

Activations Density 0.040%

references to legal proceedings or events involving hearings

occurrences of the word "hearing" and its variations

No Comments

No Known Activations