INDEX

Explanations

instances of novel concepts or functions being discussed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

脚注の使い方

-0.56

adget

-0.55

 esfor

-0.53

Heer

-0.51

ben

-0.49

возь

-0.49

Personensuche

-0.49

iecie

-0.48

 Normdatei

-0.48

 Heer

-0.48

POSITIVE LOGITS

 systematic

0.79

 Signalez

0.79

0.78

0.77

 Systematic

0.76

0.73

/***/

0.72

 Référence

0.72

Systematic

0.70

Activations Density 0.819%

instances of novel concepts or functions being discussed

No Comments

No Known Activations