INDEX

Explanations

references to legal terms and court procedures

oai_token-act-pair · gpt-3.5-turbo

instances of punctuation and their frequency within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ģĸ

-0.83

¬¼

-0.71

itone

-0.68

ãĤ¦ãĤ¹

-0.64

ary

-0.63

KEN

-0.62

-0.61

theless

-0.60

antly

-0.59

ļé

-0.59

POSITIVE LOGITS

 namely

1.01

etc

0.98

 including

0.96

huh

0.92

 albeit

0.90

 however

0.85

 which

0.81

but

0.77

eh

0.76

ie

0.75

Activations Density 0.244%

references to legal terms and court procedures

instances of punctuation and their frequency within the text

No Comments

No Known Activations