INDEX

Explanations

proper nouns refering to individuals, especially pertaining to legal or political contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Dan."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

CLASSIFIED

-0.80

 captcha

-0.73

¥ŀ

-0.72

ĺħ

-0.69

 margins

-0.69

cffffcc

-0.68

 lone

-0.68

*/(

-0.68

 actionGroup

-0.68

gettable

-0.68

POSITIVE LOGITS

forth

1.10

zig

0.96

ube

0.94

ilo

0.92

isco

0.90

alog

0.90

coni

0.89

 Marino

0.88

ovan

0.87

uba

0.85

Activations Density 0.006%

proper nouns refering to individuals, especially pertaining to legal or political contexts

occurrences of the name "Dan."

No Comments

No Known Activations