INDEX

Explanations

specific coding or mathematical constructs and values

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

+#+

-0.51

Šaltiniai

-0.51

addCriterion

-0.49

şiv

-0.47

Espèce

-0.47

__((

-0.46

'],'

-0.46

zné

-0.46

mobileqq

-0.45

това

-0.45

POSITIVE LOGITS

 myſelf

0.85

ſelves

0.80

 مشين

0.78

InjectAttribute

0.76

enumi

0.74

DockStyle

0.72

 themſelves

0.70

 Baillargeon

0.70

 syphilis

0.69

 biographer

0.69

Activations Density 0.021%

specific coding or mathematical constructs and values

No Comments

No Known Activations