INDEX

Explanations

terms related to automotive performance and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

NameValuePair

-0.52

endam

-0.50

atsby

-0.50

 ContentValues

-0.49

 franquicia

-0.49

elemField

-0.49

assign

-0.48

Svg

-0.48

Svg

-0.47

 crossbody

-0.47

POSITIVE LOGITS

 dyno

0.75

 street

0.62

 spool

0.62

dyn

0.60

Dy

0.59

 nitrous

0.58

Dy

0.58

 boost

0.57

 STREET

0.57

AFR

0.56

Activations Density 0.215%

terms related to automotive performance and specifications

No Comments

No Known Activations