INDEX

Explanations

attributes and parameters of a technical or programming nature, with a focus on data structures and functional interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 kaynağından

-0.56

élite

-0.48

 Vest

-0.48

дир

-0.46

 Dore

-0.45

 getItemCount

-0.45

 cartão

-0.45

Kor

-0.45

 albero

-0.44

waw

-0.44

POSITIVE LOGITS

\{\\

0.77

Personendaten

0.72

 Normdatei

0.70

 juventus

0.68

\}\\

0.68

</caption>

0.67

assertIn

0.66

EndContext

0.66

ticides

0.65

 HAPPENED

0.65

Activations Density 0.110%

attributes and parameters of a technical or programming nature, with a focus on data structures and functional interactions

No Comments

No Known Activations