INDEX

Explanations

phrases related to hypothetical scenarios or expectations

oai_token-act-pair · gpt-3.5-turbo

conditional or hypothetical phrases indicating expectations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

usha

-0.63

 revived

-0.60

 Cance

-0.59

ites

-0.58

iago

-0.58

sei

-0.57

gaard

-0.56

atta

-0.56

 expired

-0.56

 Phelps

-0.55

POSITIVE LOGITS

 expect

0.98

 normally

0.97

 ordinarily

0.91

 otherwise

0.90

 characterize

0.89

 tolerate

0.76

 anticipate

0.75

 deem

0.75

 imagine

0.72

 imply

0.71

Activations Density 0.099%

phrases related to hypothetical scenarios or expectations

conditional or hypothetical phrases indicating expectations

No Comments

No Known Activations