INDEX

Explanations

concepts related to evaluation and performance assessment

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ChildScrollView

-0.59

MigrationBuilder

-0.56

 GenerationType

-0.54

getDoctrine

-0.52

 gambe

-0.51

CppMethod

-0.50

featureID

-0.50

 JpaRepository

-0.49

ScopeManager

-0.48

wapV

-0.48

POSITIVE LOGITS

󠁴

0.39

zola

0.39

 worth

0.37

brid

0.37

httphttps

0.37

 /></

0.36

 Indah

0.36

tiba

0.36

Amber

0.36

 ва

0.35

Activations Density 0.110%

concepts related to evaluation and performance assessment

No Comments

No Known Activations