INDEX

Explanations

features related to automotive design and styling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 chimique

-0.50

 químico

-0.47

 šal

-0.44

 chimiques

-0.43

buty

-0.40

 instruk

-0.40

 privado

-0.40

épa

-0.40

 KeyError

-0.39

 chute

-0.39

POSITIVE LOGITS

+#+#

0.90

RegressionTest

0.73

 AssemblyTitle

0.71

__':

0.71

 disambiguazione

0.71

ConstraintMaker

0.69

SequentialGroup

0.68

setVerticalGroup

0.67

 ostavi

0.67

 препратки

0.66

Activations Density 0.112%

features related to automotive design and styling

No Comments

No Known Activations