INDEX

Explanations

formal criteria or specifications for inclusion in specific lists or classifications

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

history or stories

np_acts-logits-general · gemini-2.0-flash

history lessons and stories

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.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

LookAnd

-0.76

AntiForgeryToken

-0.73

TestingModule

-0.67

Spoljašnje

-0.62

kháu

-0.61

Chham

-0.61

قایناق‌لار

-0.60

IntoConstraints

-0.59

complexContent

-0.59

VersionUID

-0.59

POSITIVE LOGITS

 history

0.97

 historical

0.95

 histories

0.93

 stories

0.93

history

0.87

 anecdotes

0.86

Historical

0.84

 historic

0.83

 HISTOR

0.82

 storytelling

0.81

Activations Density 0.202%

formal criteria or specifications for inclusion in specific lists or classifications

history or stories

history lessons and stories

No Comments

No Known Activations