INDEX

Explanations

elements related to licensing and cookies

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

Code, rules, and abbreviations

np_acts-logits-general · gemini-2.0-flash

technical documentation and configuration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ISupport

-0.69

 mergeFrom

-0.57

 Accesat

-0.56

 esternos

-0.54

 AssemblyCulture

-0.53

webElementXpaths

-0.51

isEqualTo

-0.50

thâu

-0.49

bas

-0.48

::~

-0.47

POSITIVE LOGITS

 XNUMX

0.64

 Theses

0.62

gypti

0.59

saurus

0.59

enseignements

0.58

CppCodeGen

0.57

IGraphics

0.56

ikkert

0.55

ósfera

0.55

ufort

0.54

Activations Density 0.063%

elements related to licensing and cookies

Code, rules, and abbreviations

technical documentation and configuration

No Comments

No Known Activations