INDEX

Explanations

technical terminology and references in programming and computer science contexts

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

RegressionTest

-0.95

Diwedd

-0.87

KURZBESCHREIBUNG

-0.84

ConstraintMaker

-0.82

évaluateur

-0.81

########.

-0.80

numerusform

-0.79

 lenker

-0.78

afficheront

-0.77

 Baillargeon

-0.77

POSITIVE LOGITS

addGap

0.41

 glyphicon

0.40

sy

0.38

 mudou

0.38

rolid

0.38

ʿ

0.37

genta

0.37

TargetException

0.37

͘

0.36

Activations Density 0.302%

technical terminology and references in programming and computer science contexts

No Comments

No Known Activations