INDEX

Explanations

references to statistics or numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 HasFactory

-0.90

 Мексичка

-0.78

AsUp

-0.73

Fordítás

-0.72

dafx

-0.71

 Arkivert

-0.71

GEBURTSDATUM

-0.71

 EnglishChoose

-0.71

LookAnd

-0.70

 BitmapFactory

-0.69

POSITIVE LOGITS

0.81

’

0.79

0.60

mathrm

0.56

/>

0.56

don

0.54

 soient

0.50

begin

0.49

 Organ

0.49

COHOL

0.49

Activations Density 0.242%

references to statistics or numerical data

No Comments

No Known Activations