INDEX

Explanations

references to electric and electromagnetic concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Personensuche

-1.23

 betweenstory

-1.07

 виправивши

-1.00

็จ

-0.91

uyasha

-0.91

 GeoNames

-0.88

 AssemblyCulture

-0.87

 дописавши

-0.87

 defaultstate

-0.87

 parseFrom

-0.85

POSITIVE LOGITS

 electric

2.97

 Electric

2.84

Electric

2.71

electric

2.56

 ELECTRIC

2.44

ELECTRIC

2.19

 elektr

1.88

 electrical

1.77

 elektrische

1.71

 électrique

1.70

Activations Density 0.070%

references to electric and electromagnetic concepts

No Comments

No Known Activations