INDEX

Explanations

code-related structures and components, particularly import statements and class definitions

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

.Kt, .Set, 7F, R/\

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 disambiguazione

-0.66

ंदीखरीदारी

-0.56

 Infórmanos

-0.55

 ujednoznacz

-0.54

 <>",

-0.53

 MenuView

-0.49

 يتيمه

-0.47

ⓧ

-0.47

LookAnd

-0.47

":[{

-0.46

POSITIVE LOGITS

 Polsek

0.46

 jeugd

0.46

 jazdy

0.44

 wedstrijd

0.44

 vloer

0.44

 konkuren

0.44

 prévoir

0.43

 gedrag

0.43

 Konkurrenz

0.43

 jūsų

0.43

Activations Density 0.001%

code-related structures and components, particularly import statements and class definitions

.Kt, .Set, 7F, R/\

No Comments

No Known Activations