INDEX

Explanations

geographical locations and regional classifications

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

 kaynağından

-0.71

 disambiguazione

-0.65

 <<<<<<<<<<<<<<

-0.62

geolocation

-0.55

viewDidLoad

-0.54

thien

-0.54

JNIEnv

-0.54

variates

-0.54

GLenum

-0.53

orama

-0.52

POSITIVE LOGITS

SharedCtor

0.59

HideFlags

0.58

PyExc

0.57

 endregion

0.56

adpleegd

0.55

 fuis

0.55

//});

0.54

 Wikiseite

0.54

 podjela

0.52

IsMutable

0.51

Activations Density 0.852%

geographical locations and regional classifications

No Comments

No Known Activations