INDEX

Explanations

specific terms and codes related to geographic locations and programming structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 }}"></

-0.67

 kasarigan

-0.66

 SQLAlchemy

-0.61

 HasFactory

-0.57

 disambiguazione

-0.54

 المعيارى

-0.54

 informée

-0.53

 GenerationType

-0.53

AndEndTag

-0.52

featureID

-0.52

POSITIVE LOGITS

的问道

0.63

HasIndex

0.58

Sun

0.53

درسة

0.52

activate

0.52

Sun

0.52

以

0.52

هما

0.52

的说道

0.52

 domestiques

0.51

Activations Density 0.822%

specific terms and codes related to geographic locations and programming structures

No Comments

No Known Activations