INDEX

Explanations

code structures and keywords related to model definitions in programming

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

Xna

-0.56

(;;

-0.55

PageContext

-0.54

prnewswire

-0.49

BindView

-0.49

HStack

-0.49

GroupLayout

-0.48

 meas

-0.47

Chham

-0.47

postsleuth

-0.45

POSITIVE LOGITS

 referenties

0.93

 CreateTagHelper

0.80

sizeCache

0.75

 HttpNotFound

0.60

ecore

0.58

 Sado

0.57

TagMode

0.56

MetaType

0.56

Jîn

0.56

 supérieures

0.56

Activations Density 0.008%

code structures and keywords related to model definitions in programming

No Comments

No Known Activations