INDEX

Explanations

references to the concept of "hard work" or the adjective "hard."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ollectionView

-0.87

abestanden

-0.84

 propOrder

-0.81

 AssemblyTitle

-0.78

 BoxFit

-0.76

 ویکی‌پدیا

-0.75

 Италијани

-0.73

 PropTypes

-0.73

 ostavi

-0.72

AccessorTable

-0.72

POSITIVE LOGITS

 hard

1.48

 Hard

1.46

 HARD

1.35

Hard

1.35

HARD

1.32

hard

1.30

 harder

1.05

硬

0.98

 hardest

0.95

 hards

0.93

Activations Density 0.059%

references to the concept of "hard work" or the adjective "hard."

No Comments

No Known Activations