INDEX

Explanations

mentions of a specific format of data or code, particularly related to programming constructs or variables

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hematical

-0.88

cal

-0.75

 pinak

-0.75

 Lame

-0.71

 QLabel

-0.71

 Munster

-0.68

 Martel

-0.67

Sna

-0.66

 Wick

-0.66

 useSelector

-0.66

POSITIVE LOGITS

bf

1.21

bf

1.07

BF

1.04

BF

1.01

Bf

0.92

Bf

0.83

 Godfrey

0.76

 sujet

0.75

Koh

0.74

Koh

0.70

Activations Density 0.021%

mentions of a specific format of data or code, particularly related to programming constructs or variables

No Comments

No Known Activations