INDEX

Explanations

references to Python and database model structures in code snippets

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

user input start

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

rungsseite

-0.57

 autorytatywna

-0.56

fromnode

-0.54

ftagPool

-0.52

ModelSerializer

-0.50

StoryboardSegue

-0.50

GTCX

-0.48

MigrationBuilder

-0.48

Diweddarwch

-0.47

webElementXpaths

-0.46

POSITIVE LOGITS

geg

0.41

forChild

0.39

gotten

0.38

SearchTree

0.38

BeginInit

0.36

BAC

0.36

tren

0.35

 роз

0.35

npm

0.35

Sis

0.35

Activations Density 0.004%

references to Python and database model structures in code snippets

user input start

No Comments

No Known Activations