INDEX

Explanations

references to women with the title "Ms." followed by names

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Ms. followed by names

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

存于互联网档案馆

-0.53

afficheront

-0.52

 wireType

-0.50

 Atmosphäre

-0.50

 Verhältnisse

-0.50

iligung

-0.47

enumi

-0.47

vég

-0.46

 Gefühle

-0.46

ResumeLayout

-0.46

POSITIVE LOGITS

lorette

0.51

 Miss

0.49

ことの

0.45

Mr

0.44

 nurse

0.43

nestjs

0.43



0.42

Miss

0.42

nurse

0.42

Lady

0.41

Activations Density 0.006%

references to women with the title "Ms." followed by names

Ms. followed by names

No Known Activations