INDEX

Explanations

references to scientific terms and jargon related to biomedical and chemical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

dientemente

-0.57

 manifestazione

-0.56

DebuggerNonUser

-0.53

ónde

-0.52

 szóci

-0.52

deelte

-0.52

 ModelExpression

-0.52

konomi

-0.51

 morrer

-0.51

uarkan

-0.50

POSITIVE LOGITS

PC

0.79

حياته

0.78

brainly

0.78

 mammalian

0.73

abstract

0.73

webElementXpaths

0.72

 Mammal

0.72

 solving

0.72

PC

0.71

Mammal

0.71

Activations Density 0.057%

references to scientific terms and jargon related to biomedical and chemical concepts

No Comments

No Known Activations