INDEX

Explanations

data representations related to measurements or numerical values, especially in the context of scientific experiments

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

Japanese dialogue timestamps

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

 blood

-0.37

ion

-0.37

 fine

-0.36

elt

-0.36

<h1>

-0.34

RenderAtEndOf

-0.34

pen

-0.33

</h2>

-0.33

cid

-0.33

 Greer

-0.33

POSITIVE LOGITS

OrBuilder

0.80

 disambiguazione

0.78

SourceChecksum

0.67

 AspNetCore

0.66

PropertyChanging

0.66

SerializedSize

0.66

AndEndTag

0.65

ViewFeatures

0.64

homonymie

0.62

 Wicidata

0.61

Activations Density 0.065%

data representations related to measurements or numerical values, especially in the context of scientific experiments

Japanese dialogue timestamps

No Comments

No Known Activations