INDEX

Explanations

technical jargon related to programming and code formatting

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

odeon

-0.53

pirazione

-0.48

 ModelRenderer

-0.47

 جغرافيا

-0.46

 статистики

-0.44

Géographie

-0.43

 titolo

-0.43

Getenv

-0.42

ederal

-0.42

subequations

-0.41

POSITIVE LOGITS

TagMode

0.97

contentLoaded

0.86

 мәкалә

0.76

ThroughAttribute

0.72

 Roskov

0.71

évaluateur

0.69

艋

0.69

 tartalomajánló

0.68

resave

0.66

AndEndTag

0.66

Activations Density 0.054%

technical jargon related to programming and code formatting

No Comments

No Known Activations