INDEX

Explanations

specific questions or statements expressing uncertainty and seeking knowledge or information

oai_token-act-pair · gpt-3.5-turbo

questions about knowledge and certainty

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

athi

-0.76

bilt

-0.75

ashtra

-0.70

assi

-0.68

ahime

-0.68

 Jackets

-0.67

udeau

-0.66

phrine

-0.64

urdue

-0.64

JO

-0.64

POSITIVE LOGITS

 beforehand

0.84

 whats

0.79

 whether

0.78

 guesses

0.75

worthiness

0.75

how

0.75

estamp

0.73

 exactly

0.70

checked

0.69

 detect

0.68

Activations Density 0.212%

specific questions or statements expressing uncertainty and seeking knowledge or information

questions about knowledge and certainty

No Comments

No Known Activations