INDEX

Explanations

conjunctions in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 externi

-0.76

 contrário

-0.55

 supérieurs

-0.55

 stessa

-0.54

ıştı

-0.54

 zelve

-0.54

 supérieures

-0.54

 vicenda

-0.54

 stesso

-0.53

featureID

-0.52

POSITIVE LOGITS

aspectj

0.62

BorderLayout

0.61

SpringRunner

0.59

ChildScrollView

0.58

gebras

0.57

cèse

0.56

EnableWeb

0.56

providedIn

0.56

EndInit

0.55

 Audiodateien

0.55

Activations Density 0.209%

conjunctions in the text

No Comments

No Known Activations