INDEX

Explanations

occurrences of the term "normalize" and its variations in context

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

normalize or normalized

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

 FileNotFound

-0.48

AppComponent

-0.46

playerId

-0.46

ipAddress

-0.45

 getFile

-0.43

imread

-0.43

sessionId

-0.42

-0.40

eventId

-0.40

POSITIVE LOGITS

normalize

1.03

 Normalize

1.02

Normalize

0.99

 normalize

0.98

 normalization

0.92

 Normalized

0.86

 normalized

0.79

Normalization

0.78

 Normal

0.77

normalized

0.76

Activations Density 0.017%

occurrences of the term "normalize" and its variations in context

normalize or normalized

No Comments

No Known Activations