INDEX

Explanations

terms related to chemical or physical properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 للاسماء

-0.78

OGND

-0.77

+:+

-0.75

uxxxx

-0.67

 Reverso

-0.67

 WWII

-0.67

 drapes

-0.66

 trajets

-0.66

SourceChecksum

-0.66

 hooves

-0.64

POSITIVE LOGITS

 employés

0.59

 ordinaire

0.51

æ

0.49

 afterwards

0.48

 theils

0.48

væ

0.48

 débris

0.48

 ordinaria

0.47

 fine

0.46

 brano

0.46

Activations Density 0.342%

terms related to chemical or physical properties

No Comments

No Known Activations