INDEX

Explanations

numerical data and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

/>";

-0.71

 dài

-0.70

 Lightfoot

-0.70

 vors

-0.68

حياته

-0.68

subpackage

-0.66

 AssemblyProduct

-0.66

 مصرى

-0.65

Jody

-0.65

Mant

-0.65

POSITIVE LOGITS

 nucleation

0.83

Zer

0.80

 nought

0.77

 hemlock

0.76

 eczema

0.76

Портали

0.73

0.72

 skulls

0.71

 Ersten

0.70

marines

0.70

Activations Density 1.093%

numerical data and measurements

No Comments

No Known Activations

numerical data and measurements

No Comments

No Known Activations