INDEX

Explanations

numerical or tabular data relevant to various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LookAnd

-0.64

 Geraadpleegd

-0.56

popularity

-0.55

üns

-0.54

Hozzáférés

-0.54

SpringBootTest

-0.51

awtextra

-0.50

 Normdatei

-0.50

WebVitals

-0.48

CGRectMake

-0.48

POSITIVE LOGITS

enumii

0.74

bcryptjs

0.72

 personalizadas

0.57

 وتسجيلات

0.55

 Мексичка

0.53

jarati

0.53

lujah

0.52

Chham

0.50

OCO

0.48

ToRead

0.48

Activations Density 0.292%

numerical or tabular data relevant to various contexts

No Comments

No Known Activations