INDEX

Explanations

references to the name "Katherine" and associated identifiers or locations

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

Katherine names and Karnofsky scale

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

didSet

-0.65

LLocation

-0.62

 ProtoMessage

-0.58

quele

-0.55

onedDateTime

-0.54

setupUi

-0.53

 termica

-0.50

jenigen

-0.50

 Kunt

-0.49

Tikang

-0.49

POSITIVE LOGITS

tC

0.49

 Blackwell

0.48

pD

0.48

kulu

0.47

 Bristol

0.47

0.46

 Skye

0.44

 Bhatt

0.44

others

0.43

timi

0.43

Activations Density 0.078%

references to the name "Katherine" and associated identifiers or locations

Katherine names and Karnofsky scale

No Comments

No Known Activations