INDEX

Explanations

references to administrative processes and delays in documentation or procedural 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anmoins

-0.53

出版年

-0.52

CPM

-0.52

<bos>

-0.51

 Bioaccumulative

-0.49

("/");

-0.48

CPM

-0.48

 musicale

-0.47

 alko

-0.47

Already

-0.46

POSITIVE LOGITS

 slow

0.80

 delay

0.73

 Slow

0.71

 slower

0.71

 delays

0.70

 demora

0.67

slow

0.67

 slowest

0.67

 delayed

0.66

Slow

0.66

Activations Density 0.234%

references to administrative processes and delays in documentation or procedural contexts

No Comments

No Known Activations