INDEX

Explanations

comparative words denoting degree, such as "more," "less," "better," and "much."

oai_token-act-pair · gpt-3.5-turbo

comparative terms indicating quantity or degree

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jen

-0.77

inet

-0.74

ystem

-0.70

ī

-0.68

merce

-0.67

 Supplement

-0.66

innacle

-0.63

hemer

-0.63

bis

-0.62

early

-0.62

POSITIVE LOGITS

 knack

0.96

 chance

0.95

 aspirations

0.95

 ambitions

0.94

 patience

0.92

 luck

0.90

 doubts

0.89

 intentions

0.89

 guts

0.89

 clout

0.87

Activations Density 0.307%

comparative words denoting degree, such as "more," "less," "better," and "much."

comparative terms indicating quantity or degree

No Comments

No Known Activations