INDEX

Explanations

whitespace characters in the text

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

Code-related tokens

np_acts-logits-general · gemini-2.0-flash

ngx http probe

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 industriels

-0.66

 ostavi

-0.65

 déplacements

-0.64

homonymie

-0.63

 réguli

-0.63

 nucléaire

-0.62

 spéciaux

-0.61

 étan

-0.61

 ainfi

-0.61

 automatiques

-0.60

POSITIVE LOGITS

0.54

TagHelpers

0.53

glGen

0.51

/**

0.51

prepareStatement

0.51

SuppressLint

0.51

Портал

0.50

didReceive

0.49

cences

0.48

!*\

0.47

Activations Density 0.159%

whitespace characters in the text

Code-related tokens

ngx http probe

No Comments

No Known Activations