INDEX

Explanations

structures related to programming or computational logic

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

Datuak

-1.07

 متعلقه

-0.80

 nawr

-0.76

-0.75

expandindo

-0.73

jsii

-0.72

 مرئيه

-0.72

 <>",

-0.67

 IndexPath

-0.66

setVerticalGroup

-0.66

POSITIVE LOGITS

 esternos

0.50

An

0.48

timeouts

0.47

Promises

0.46

ът

0.45

 colazione

0.44

 success

0.41

 River

0.41

AntiForgeryToken

0.40

Activations Density 0.053%

structures related to programming or computational logic

No Comments

No Known Activations

structures related to programming or computational logic

No Comments

No Known Activations