INDEX

Explanations

phrases or sentences ending with a dramatic or impactful statement

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Wait" used in dialogue or conversational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

reb

-0.74

ãĤº

-0.72

audi

-0.70

insula

-0.65

sports

-0.65

rosse

-0.64

urgical

-0.63

 Instr

-0.63

ighter

-0.63

ffic

-0.62

POSITIVE LOGITS

wait

0.95

 patiently

0.94

 wait

0.86

 Wait

0.81

ruciating

0.80

resses

0.79

eful

0.77

ressing

0.76

 impatient

0.72

erness

0.72

Activations Density 0.020%

phrases or sentences ending with a dramatic or impactful statement

instances of the word "Wait" used in dialogue or conversational contexts

No Comments

No Known Activations