INDEX

Explanations

identifiers related to maps and locations

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

geographic names and identifiers

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

 results

-0.40

vencia

-0.39

ed

-0.39

 demands

-0.38

 camadas

-0.38

 charts

-0.37

 chart

-0.37

짐

-0.35

 result

-0.35

POSITIVE LOGITS

 ModelExpression

0.73

ViewImports

0.71

httphttps

0.69

KURZBESCHREIBUNG

0.67

出版年

0.66

########.

0.66

="@+

0.64

 transfieras

0.57

 للاسماء

0.56

Ārējās

0.56

Activations Density 0.011%

identifiers related to maps and locations

geographic names and identifiers

No Comments

No Known Activations