INDEX

Explanations

references to figures and tables in scientific texts

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

 nakalista

-0.73

таратура

-0.71

 <>",

-0.70

 BoxFit

-0.67

AlterField

-0.66

FXML

-0.65

TintMode

-0.63

twimg

-0.63

']));

-0.62

writeFieldEnd

-0.61

POSITIVE LOGITS

存于互联网档案馆

0.45

zumaki

0.45

 poleg

0.43

pherals

0.42

beelding

0.41

Denomin

0.41

Meet

0.41

 sabbia

0.41

帖最后由

0.40

صفات

0.40

Activations Density 0.863%

references to figures and tables in scientific texts

No Comments

No Known Activations