INDEX

Explanations

questions posed in a somewhat dramatic or urgent manner

oai_token-act-pair · gpt-3.5-turbo

rhetorical questions and expressions of uncertainty

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

://

-0.72

REM

-0.60

vant

-0.60

visors

-0.59

charg

-0.59

 Mansion

-0.58

liner

-0.58

cin

-0.57

PORT

-0.56

 veterans

-0.56

POSITIVE LOGITS

 exactly

0.96

 somew

0.89

 pray

0.87

 whence

0.79

 anyway

0.74

WHY

0.73

 precisely

0.73

uh

0.71

oh

0.70

 Exactly

0.69

Activations Density 0.065%

questions posed in a somewhat dramatic or urgent manner

rhetorical questions and expressions of uncertainty

No Comments

No Known Activations