INDEX

Explanations

titles and ranks related to military and authority figures

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

Titles before names

np_acts-logits-general · gemini-2.0-flash

titles followed by names

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

 façons

-0.51

 GetEnumerator

-0.45

 peint

-0.43

OnAdd

-0.42

 htons

-0.42

 nltk

-0.42

 true

-0.42

IConfiguration

-0.41

 déclaration

-0.41

sinon

-0.40

POSITIVE LOGITS

 '\\;'

0.89

:✨

0.85

 صوتيه

0.81

 kasarigan

0.77

LookAnd

0.75

ContentAsync

0.74

 Signalez

0.73

 distanciation

0.72

 betweenstory

0.72

 дописавши

0.71

Activations Density 0.115%

titles and ranks related to military and authority figures

Titles before names

titles followed by names

No Comments

No Known Activations