INDEX

Explanations

programming-related terms and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 SIMBAD

-0.60

RegressionTest

-0.56

INSON

-0.56

 '\\;'

-0.55

liothèque

-0.54

 JpaRepository

-0.53

 مكتبه

-0.49

–

-0.48

<bos>

-0.48

—

-0.47

POSITIVE LOGITS

 Exacts

0.79

ArgsConstructor

0.79

ConstraintMaker

0.78

ButterKnife

0.73

SequentialGroup

0.73

complexType

0.71

Revenir

0.71

Tikang

0.71

ValueStyle

0.70

 <<<<<<<<<<<<<<

0.68

Activations Density 0.065%

programming-related terms and functions

No Comments

No Known Activations