INDEX

Explanations

technical terms and jargon

oai_token-act-pair · gpt-3.5-turbo

mentions of disagreements, controversies, or disputes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 touches

-0.76

 shroud

-0.71

 nude

-0.71

 collecting

-0.69

 reception

-0.68

 Borough

-0.68

 clad

-0.68

weights

-0.66

 Downs

-0.66

 buggy

-0.65

POSITIVE LOGITS

¬

1.02

¹

1.00

£

1.00

Ĥ

1.00

»

0.96

º

0.95

į

0.94

½

0.93

ONSORED

0.92

ķ

0.92

Activations Density 0.131%

technical terms and jargon

mentions of disagreements, controversies, or disputes

No Comments

No Known Activations