INDEX

Explanations

sections of text that reference code or programming concepts

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

 Preferencias

-0.46

 Conce

-0.45

 hush

-0.45

 Entomol

-0.45

zl

-0.44

 Principle

-0.43

irse

-0.42

entir

-0.41

zoll

-0.41

ysaccharide

-0.41

POSITIVE LOGITS

 MainAxisSize

0.96

 ModelExpression

0.86

 referenties

0.78

oredCriteria

0.75

 للاسماء

0.75

 ویکی‌پدیا

0.75

stateMutability

0.74

SharedCtor

0.74

abestanden

0.72

Източници

0.70

Activations Density 0.043%

sections of text that reference code or programming concepts

No Comments

No Known Activations