INDEX

Explanations

instances of the character 'w' in various forms and contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Following "w" and related symbols like "wrt"

np_acts-logits-general · gemini-2.0-flash

wrt and mathematical expressions

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

Negative Logits

DockStyle

-0.87

WebVitals

-0.84

HostException

-0.66

 cauſe

-0.64

 purpoſe

-0.63

ElementException

-0.63

GraphicsUnit

-0.59

InputBorder

-0.59

 оригіналу

-0.59

 Bioaccumulative

-0.58

POSITIVE LOGITS

olis

0.48

nim

0.47

Nii

0.46

ariant

0.45

spar

0.43

cale

0.43

nim

0.42

kita

0.42

kloped

0.42

 then

0.41

Activations Density 0.090%

instances of the character 'w' in various forms and contexts

Following "w" and related symbols like "wrt"

wrt and mathematical expressions

No Known Activations