INDEX

Explanations

coding and comparison-related terms and syntax

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

comparison and sorting

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

UserScript

-0.50

pshot

-0.42

怎麼辦

-0.40

uppa

-0.39

 sectional

-0.39

的结果

-0.38

GRO

-0.38

RTCK

-0.38

laut

-0.37

 sambung

-0.37

POSITIVE LOGITS

 kiệm

0.47

 Partagez

0.46

ThemeOverlay

0.40

ValueStyle

0.40

 doInBackground

0.40

 ContentValues

0.40

ChildScrollView

0.39

 compareTo

0.38

 collectons

0.38

 viewType

0.38

Activations Density 0.007%

coding and comparison-related terms and syntax

comparison and sorting

No Comments

No Known Activations