INDEX

Explanations

statements that contain definitive claims or conclusions

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

 also

-0.59

δου

-0.52

pacs

-0.52

cesis

-0.52

σθαι

-0.51

 benefit

-0.50

 utama

-0.48

 EdgeInsets

-0.48

 entanto

-0.48

Funciones

-0.46

POSITIVE LOGITS

AndEndTag

0.76

StoryboardSegue

0.76

 समीक्षक

0.73

RenderAtEndOf

0.69

 فريبيس

0.66

 makeStyles

0.66

 referenties

0.65

--)

0.63

 Paglinawan

0.62

 "..\..\..\

0.62

Activations Density 0.365%

statements that contain definitive claims or conclusions

No Comments

No Known Activations