INDEX

Explanations

specific formatting characters or symbols used in programming or markup languages

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

 Signalez

-0.78

 MainAxisSize

-0.69

OGND

-0.66

TagMode

-0.59

 Taktlose

-0.59

 Normdatei

-0.56

SequentialGroup

-0.55

DockStyle

-0.55

RenderAtEndOf

-0.53

awtextra

-0.52

POSITIVE LOGITS

0.48

0.43

 Soler

0.37

 Svensson

0.36

Indian

0.34

artal

0.34

ierz

0.33

 Fonseca

0.33

Min

0.33

 Indian

0.33

Activations Density 0.000%

specific formatting characters or symbols used in programming or markup languages

<start_of_turn> user

No Comments

No Known Activations