INDEX

Explanations

references to research proceedings and conferences

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

帖最后由

-0.55

 dég

-0.48

 rép

-0.46

 BUREAU

-0.45

 dễ

-0.44

府

-0.44

oxone

-0.44

weder

-0.43

zeti

-0.43

hub

-0.41

POSITIVE LOGITS

 proceedings

0.92

 Proceedings

0.85

 conference

0.77

ceedings

0.74

 Proceeding

0.74

Datuak

0.73

 conférence

0.72

Proceedings

0.70

Conference

0.67

antlr

0.67

Activations Density 0.256%

references to research proceedings and conferences

No Comments

No Known Activations