INDEX

Explanations

instances of the letter 'g' or words containing 'g'

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

addContainerGap

-0.76

 AspNetCore

-0.75

ValueStyle

-0.74

GEBURTSDATUM

-0.71

 "..\..\

-0.70

 AssemblyTitle

-0.69

+#+#

-0.67

esModule

-0.67

/**

-0.66

 nahilalakip

-0.65

POSITIVE LOGITS

 livré

0.48

yr

0.47

GmbH

0.45

Truth

0.43

 Relative

0.43

urante

0.43

 élastique

0.42

 Poids

0.42

 Longueur

0.42

Explanation

0.42

Activations Density 0.311%

instances of the letter 'g' or words containing 'g'

No Comments

No Known Activations