INDEX

Explanations

references to code components or image-related terms in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 propOrder

-0.73

MergeFrom

-0.66

makeConstraints

-0.62

 propTypes

-0.60

 שוליים

-0.58

 ujednoznacz

-0.57

 للمعارف

-0.57

нгредієнти

-0.56

 onOptions

-0.56

ArgsConstructor

-0.56

POSITIVE LOGITS

 imageNamed

0.65

FileDescriptor

0.62

Xna

0.57

tals

0.54

MessageOf

0.48

SpringBootTest

0.47

mtrl

0.46

 pulmonar

0.44

ResourceManager

0.44

 Sternen

0.44

Activations Density 0.415%

references to code components or image-related terms in programming contexts

No Comments

No Known Activations