INDEX

Explanations

code structures involving method definitions and returns

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

getter return statements

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

続きます

-0.40

 ympä

-0.39

guiente

-0.37

 nuvem

-0.36

ambién

-0.35

glMatrixMode

-0.35

 cappuccio

-0.35

 câmera

-0.35

 punggung

-0.34

 árvore

-0.33

POSITIVE LOGITS

OGND

0.83

SharedDtor

0.75

verwijspagina

0.71

 <<<<<<<<<<<<<<

0.66

\{\\

0.65

ReusableCell

0.63

 EconPapers

0.60

__(/*!

0.60

tubers

0.58

حياته

0.57

Activations Density 0.004%

code structures involving method definitions and returns

getter return statements

No Comments

No Known Activations