INDEX

Explanations

references to claims and established protocols in scientific contexts

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

 >=",

-0.67

MLLoader

-0.51

MediaStore

-0.49

Bronnen

-0.46

GraphicsUnit

-0.44

ocarp

-0.43

XMLSchema

-0.43

 giản

-0.42

 réessayer

-0.40

 Even

-0.40

POSITIVE LOGITS

 betweenstory

0.78

expandindo

0.78

 насељу

0.73

 Paglinawan

0.71

indd

0.60

 Reactor

0.59

 theirs

0.59

сылкі

0.58

</tfoot>

0.57

슷

0.57

Activations Density 0.450%

references to claims and established protocols in scientific contexts

No Comments

No Known Activations