INDEX

Explanations

negative assessments of events or entities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WebServlet

-0.65

EKG

-0.51

 quotidien

-0.51

 daily

-0.49

 quotidi

-0.48

 препратки

-0.46

 bientôt

-0.46

 diariamente

-0.45

 handleMessage

-0.45

 Einrichtung

-0.43

POSITIVE LOGITS

 unusually

0.83

 unprecedented

0.74

Unusual

0.70

 يتيمه

0.70

 unusual

0.69

 inusual

0.68

 Paglinawan

0.66

precedented

0.66

AndEndTag

0.65

 exceptionally

0.64

Activations Density 0.349%

negative assessments of events or entities

No Comments

No Known Activations