INDEX

Explanations

references to academic qualifications and degrees

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

former education and roles

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

esModule

-0.54

SourceChecksum

-0.47

SBATCH

-0.46

matchCondition

-0.45

 Chwiliwch

-0.45

richTextPanel

-0.44

 defaultstate

-0.44

+#+#

-0.43

 patrones

-0.41

preventDefault

-0.41

POSITIVE LOGITS

Spin

0.38

 Stoke

0.38

 itſelf

0.38

 Spyder

0.38

xf

0.37

 ftre

0.37

ſy

0.37

 iſt

0.37

 NSString

0.37

?>>

0.37

Activations Density 0.012%

references to academic qualifications and degrees

former education and roles

No Comments

No Known Activations