INDEX

Explanations

phrases related to engagement and participation in activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

évaluateur

-0.57

Sabah

-0.53

 regular

-0.51

 normal

-0.48

 Durand

-0.45

downcase

-0.45

antMatchers

-0.45

AMP

-0.44

ће

-0.44

chartInstance

-0.43

POSITIVE LOGITS

DockStyle

0.99

 مشين

0.81

 متعلقه

0.76

 ویکی‌پدیای

0.76

PerformLayout

0.75

AccessorTable

0.74

)_/¯

0.74

0.72

例文帳に追加

0.72

 дописавши

0.72

Activations Density 0.037%

phrases related to engagement and participation in activities

No Comments

No Known Activations