INDEX

Explanations

references to names and titles, especially in the context of media or achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 recommandée

-0.59

 grav

-0.49

련

-0.47

 حص

-0.47

templateUrl

-0.46

 кори

-0.44

:][

-0.44

StringVar

-0.44

整

-0.44

 JAKARTA

-0.44

POSITIVE LOGITS

 lesser

0.76

 unimportant

0.76

astéroïdes

0.71

SBATCH

0.70

Tikang

0.69

CPtr

0.69

 disambiguazione

0.69

 mundane

0.67

AsUp

0.66

 minor

0.66

Activations Density 0.682%

references to names and titles, especially in the context of media or achievements

No Comments

No Known Activations