INDEX

Explanations

activities related to watching or using media

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

гне

-0.53

すぎた

-0.52

 Fuentes

-0.52

 labor

-0.51

 Unexpected

-0.50

 result

-0.50

ikala

-0.49

 Scha

-0.49

 ευ

-0.48

וויק

-0.48

POSITIVE LOGITS

 мәкал

0.82

сылкі

0.78

Rüyada

0.74

 Theſe

0.74

Vidite

0.73

migrationBuilder

0.72

IntoConstraints

0.70

forChild

0.69

 dépens

0.69

 Shakspeare

0.69

Activations Density 0.766%

activities related to watching or using media

No Comments

No Known Activations