INDEX

Explanations

mentions of accountability or responsibility for actions

oai_token-act-pair · gpt-3.5-turbo

instances of formal or informative content, particularly in the context of descriptions or accounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Government

-0.71

.","

-0.71

");

-0.67

itaire

-0.64

\"

-0.64

Manufact

-0.63

kefeller

-0.62

Increase

-0.62

`.

-0.61

government

-0.61

POSITIVE LOGITS

 Dunham

0.80

 gigg

0.79

 chuckled

0.78

 reply

0.77

 amused

0.77

yrics

0.77

 laughs

0.77

 replies

0.77

 Gawker

0.76

 Whedon

0.75

Activations Density 1.205%

mentions of accountability or responsibility for actions

instances of formal or informative content, particularly in the context of descriptions or accounts

No Comments

No Known Activations