INDEX

Explanations

references to statistical or numerical data in research contexts

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

URLs and web addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 betweenstory

-0.65

әрмәләр

-0.58

AsUp

-0.56

 resourceCulture

-0.54

Portail

-0.54

transQ

-0.52

 ErrIntOverflow

-0.52

HomeAsUpEnabled

-0.52

TagMode

-0.52

rrggbb

-0.52

POSITIVE LOGITS

同じく

0.43

RTGC

0.40

fu

0.39

WS

0.38

 furnished

0.38

det

0.38

jsp

0.37

 Tear

0.37

Pe

0.37

 tear

0.37

Activations Density 0.176%

references to statistical or numerical data in research contexts

URLs and web addresses

No Comments

No Known Activations