INDEX

Explanations

exclamatory statements or strong reactions

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

technical terms and numbers

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

 defaultstate

-0.59

tableFuture

-0.50

NUMX

-0.50

 jScrollPane

-0.48

AutoScaleMode

-0.48

FieldBuilder

-0.48

 Signalez

-0.47

 sexuales

-0.47

abetes

-0.44

 ब्रेकडाउन

-0.44

POSITIVE LOGITS

 AssemblyTitle

0.56

VYMaps

0.41

jit

0.41



0.40

 ModelExpression

0.38

jst

0.38

 transférez

0.37

 flat

0.37

tagHelperRunner

0.36

وفاته

0.36

Activations Density 0.000%

exclamatory statements or strong reactions

technical terms and numbers

No Comments

No Known Activations