INDEX

Explanations

unusual occurrences or deviations from normal patterns

oai_token-act-pair · gpt-3.5-turbo

the adverb "normally" indicating typical behavior or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Kut

-0.80

Ing

-0.79

ged

-0.70

 Yose

-0.66

 populism

-0.65

 Muse

-0.65

gets

-0.65

 Crusade

-0.64

addons

-0.63

 Nuggets

-0.63

POSITIVE LOGITS

llular

0.94

 behaved

0.83

 inclined

0.77

 disclaim

0.77

 partName

0.75

 encountered

0.75

adal

0.73

 reacted

0.72

hattan

0.72

 speaking

0.71

Activations Density 0.013%

unusual occurrences or deviations from normal patterns

the adverb "normally" indicating typical behavior or conditions

No Comments

No Known Activations