INDEX

Explanations

Java-related code elements and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

OCCURRED

-0.65

зулта

-0.56

 Roskov

-0.54

ьаж

-0.53

EFAULT

-0.53

 Rider

-0.52

IconModule

-0.52

mergeFrom

-0.52

:✨

-0.51

 pylint

-0.50

POSITIVE LOGITS

annotation

0.64

 виправивши

0.60

 EconPapers

0.57

awtextra

0.57

 Baillargeon

0.51

asztal

0.49

 cref

0.47

 LUMP

0.47

 anchor

0.47

Население

0.47

Activations Density 0.076%

Java-related code elements and structure

No Comments

No Known Activations