INDEX

Explanations

elements related to structured data or programming related keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ValueStyle

-0.78

 Chwiliwch

-0.73

 виправивши

-0.72

PropertyChanging

-0.69

WriteTagHelper

-0.67

matchCondition

-0.67

SequentialGroup

-0.65

ftagPool

-0.64

AddTagHelper

-0.64

 disambiguazione

-0.63

POSITIVE LOGITS

بوابة

0.69

AnchorStyles

0.60

 avoient

0.55

ftance

0.54

 Inscrivez

0.53

RESUMO

0.51

 hábiles

0.50

Portail

0.50

 profondità

0.50

 Tamanho

0.49

Activations Density 0.583%

elements related to structured data or programming related keywords

No Comments

No Known Activations