INDEX

Explanations

specific formatting or styling attributes in code, particularly related to margins and dimensions

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

2mu mathematical expressions

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

 CURLOPT

-0.42

 المعيارى

-0.39

ServletConfig

-0.36

 venuto

-0.35

Reg

-0.35

JspWriter

-0.35

 Central

-0.33

reg

-0.33

won

-0.33

 समीक्षाएं

-0.33

POSITIVE LOGITS

spacing

0.88

Jereo

0.77

 spacing

0.71

 propOrder

0.60

Spacing

0.56

 Spacing

0.56

 للاسماء

0.51

BufferException

0.49

хьтан

0.48

NameInMap

0.48

Activations Density 0.002%

specific formatting or styling attributes in code, particularly related to margins and dimensions

2mu mathematical expressions

No Comments

No Known Activations