INDEX

Explanations

documents with no notable content or activations

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

Code, references, or questions

np_acts-logits-general · gemini-2.0-flash

references and sources

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.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

kháu

-1.00

 iprot

-0.73

Попис

-0.70

kloped

-0.69

liothèque

-0.67

كويكب

-0.65

DrawerToggle

-0.61

цезда

-0.61

InsertCommand

-0.59

unknownFields

-0.58

POSITIVE LOGITS

tvguidetime

1.78

Hochspringen

1.69

مصادر

1.65

 références

1.53

 שוליים

1.53

Lähteet

1.51

مراجع

1.50

脚注の使い方

1.47

Einzelnachweise

1.45

المراجع

1.42

Activations Density 0.018%

documents with no notable content or activations

Code, references, or questions

references and sources

No Comments

No Known Activations