INDEX

Explanations

phrases indicating uncertainty or lack of definitive knowledge

oai_token-act-pair · gpt-3.5-turbo

phrases expressing uncertainty or conjecture

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

soever

-0.70

-0.63

venants

-0.62

LAB

-0.59

orbit

-0.57

marine

-0.56

orld

-0.54

CLE

-0.54

mare

-0.54

POSITIVE LOGITS

bidden

1.07

 example

0.97

geries

0.97

gery

0.96

 instance

0.95

 awhile

0.88

gettable

0.80

instance

0.78

 reasons

0.78

 starters

0.76

Activations Density 0.199%

phrases indicating uncertainty or lack of definitive knowledge

phrases expressing uncertainty or conjecture

No Comments

No Known Activations