INDEX

Explanations

references to measurements or data values

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

 ویکی‌پدیای

-0.66

 Integrals

-0.49

 bezeichneter

-0.49

liebte

-0.48

цена

-0.46

AR

-0.46

 ouder

-0.45

Suara

-0.45

 AssemblyTitle

-0.45

 chắn

-0.45

POSITIVE LOGITS

NOPQRST

0.71

\{\\

0.67

 GenerationType

0.66

writeFieldEnd

0.65

 Administrativna

0.63

PostExecute

0.61

Traceback

0.61

 ComVisible

0.59

InsertCommand

0.55

ControllerAdvice

0.55

Activations Density 0.002%

references to measurements or data values

No Comments

No Known Activations