INDEX

Explanations

phrases indicating significant events or changes

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

fixing up

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

 linkovi

-0.44

FontOfSize

-0.43

رشف

-0.42

الإنجليزية

-0.41

 TextInputType

-0.40

########.

-0.39

 الرياضيه

-0.37

GraphicsUnit

-0.36

演

-0.35

 通販

-0.34

POSITIVE LOGITS

 wrecked

0.49

httphttps

0.48

Parcelize

0.47

 défis

0.45

cleaning

0.45

Shock

0.45

Kondisi

0.44

shocked

0.44

landscape

0.44

ebabkan

0.43

Activations Density 0.028%

phrases indicating significant events or changes

fixing up

No Comments

No Known Activations