INDEX

Explanations

mentions of weapons, tools, and objects associated with sharpness or combat

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

preceding uses of force or weapons

np_acts-logits-general · gemini-2.0-flash

weapons, time, and nomenclature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 оригіналу

-0.52

ث

-0.49

 محفوظة

-0.47

 gehö

-0.47

getBean

-0.44

ancies

-0.44

kega

-0.42

 Krieges

-0.42

 forgiven

-0.41

_^

-0.41

POSITIVE LOGITS

adpleegd

0.91

Personendaten

0.82

 wielded

0.80

脚注の使い方

0.76

IVEREF

0.74

 AssemblyCulture

0.74

 ligiloj

0.73

 bearer

0.72

PMailer

0.72

CloseOperation

0.72

Activations Density 0.446%

mentions of weapons, tools, and objects associated with sharpness or combat

preceding uses of force or weapons

weapons, time, and nomenclature

No Comments

No Known Activations