INDEX

Explanations

phrases related to the concept of separation or dividing elements in various contexts

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

separation and separating components

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

دانشنامهٔ

-0.49

 informée

-0.48

Cyclo

-0.46

clientWidth

-0.45

Mouse

-0.45

currentDate

-0.44

minWidth

-0.44

xler

-0.44

imakasih

-0.44

 Mouse

-0.44

POSITIVE LOGITS

 separation

1.04

 Separation

1.00

 separating

1.00

 Separator

0.92

 separator

0.92

 separa

0.91

 separated

0.89

 séparation

0.87

separation

0.87

 separations

0.87

Activations Density 0.027%

phrases related to the concept of separation or dividing elements in various contexts

separation and separating components

No Comments

No Known Activations