INDEX

Explanations

references to death and mourning

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

death

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

vip

-0.40

 lyrical

-0.38

 nicole

-0.35

sog

-0.35

 nomenclature

-0.35

듈

-0.35

룹

-0.35

ClCompile

-0.35

 raga

-0.34

autique

-0.34

POSITIVE LOGITS

principalColumn

0.51

 laſſen

0.49

midler

0.49

ollary

0.48

 varandra

0.48

 increí

0.48

PerformLayout

0.47

 Infór

0.47

 kepad

0.46

 muerte

0.46

Activations Density 0.006%

references to death and mourning

death

No Comments

No Known Activations