INDEX

Explanations

references to stock market performance indicators and company names

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

proper names and places

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 Paglinawan

-0.76

MENAFN

-0.68

PerformLayout

-0.67

 StatefulWidget

-0.66

DropTable

-0.65

 GenerationType

-0.63

bootstrapcdn

-0.63

ceus

-0.58

 betweenstory

-0.58

ViewById

-0.57

POSITIVE LOGITS

\{\\

0.66

+//

0.56

 correctes

0.55

 estimés

0.55

 should

0.52

zaamheid

0.52

 perhaps

0.52

 maybe

0.51

imo

0.51

Activations Density 0.135%

references to stock market performance indicators and company names

proper names and places

No Comments

No Known Activations