INDEX

Explanations

phrases related to the potential effects, impacts, and outcomes of various actions or circumstances

oai_token-act-pair · gpt-3.5-turbo

phrases indicating significant impacts or effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ĸļ

-0.75

Kut

-0.69

 Britann

-0.69

udeb

-0.65

-0.64

orem

-0.63

phis

-0.62

bern

-0.60

utsche

-0.60

Jur

-0.60

POSITIVE LOGITS

 tricky

0.94

 unpredictable

0.88

 harmful

0.86

 perilous

0.86

 stressful

0.85

 dangerous

0.84

 downright

0.84

 daunting

0.83

 transformative

0.83

 misleading

0.82

Activations Density 0.313%

phrases related to the potential effects, impacts, and outcomes of various actions or circumstances

phrases indicating significant impacts or effects

No Comments

No Known Activations