INDEX

Explanations

numerical data or statistics

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

<start_of_turn>user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

참고

-0.49

 Persson

-0.47

 Zeller

-0.44

 cellular

-0.43

arsk

-0.41

 Randall

-0.41

("")]

-0.41

so

-0.40

 illegal

-0.40

THISDAY

-0.40

POSITIVE LOGITS

PerformLayout

0.67

:✨

0.61

verifyException

0.51

دانشنامهٔ

0.51

 FontWeight

0.51

GEBURTS

0.51

 Inscrivez

0.49

 userSchema

0.49

setVerticalGroup

0.47

MessageOf

0.47

Activations Density 0.000%

numerical data or statistics

<start_of_turn>user

No Comments

No Known Activations