INDEX

Explanations

verbs in the past tense that describe observation or visual perception

oai_token-act-pair · gpt-3.5-turbo

instances of the word "seen"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

prime

-0.73

atto

-0.71

aults

-0.68

vernment

-0.66

trap

-0.66

angan

-0.64

cÃ©

-0.64

angu

-0.63

airs

-0.62

cult

-0.62

POSITIVE LOGITS

 Seen

0.97

 seen

0.91

seeing

0.84

 seeing

0.75

ãĤ¼

0.75

Īè

0.74

swick

0.70

IRT

0.70

DragonMagazine

0.70

 Ceres

0.69

Activations Density 0.026%

verbs in the past tense that describe observation or visual perception

instances of the word "seen"

No Comments

No Known Activations