INDEX

Explanations

instances where someone is likely or willing to do something

oai_token-act-pair · gpt-3.5-turbo

phrases expressing willingness or tendency towards actions or opinions

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

soDeliveryDate

-0.68

Mek

-0.67

illin

-0.65

Nak

-0.64

oufl

-0.64

CHA

-0.63

mson

-0.63

original

-0.62

apeake

-0.61

arer

-0.61

POSITIVE LOGITS

 inclined

1.01

irection

0.86

 toward

0.86

ĺħ

0.86

 towards

0.83

¿½

0.76

 thereto

0.73

 leaning

0.73

igible

0.73

Ń·

0.71

Activations Density 0.034%

instances where someone is likely or willing to do something

phrases expressing willingness or tendency towards actions or opinions

No Comments

No Known Activations