INDEX

Explanations

scientific notations and measurements

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

units of measurement including prefixes

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

 betweenstory

-0.82

 queſta

-0.79

RegressionTest

-0.76

 виправивши

-0.72

featureID

-0.68

:✨

-0.65

 BorderRadius

-0.62

tanleria

-0.60

transQ

-0.60

tagHelperRunner

-0.60

POSITIVE LOGITS

 dotyczy

0.43

 pères

0.35

Lihat

0.35

 buurt

0.35

amaño

0.33

 Constitución

0.33

 Abteilung

0.33

 bahía

0.33

icznie

0.32

 internetowa

0.31

Activations Density 0.006%

scientific notations and measurements

units of measurement including prefixes

No Comments

No Known Activations