INDEX

Explanations

expressions of learning and personal development experiences

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

preparedness, confidence, learning

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

Бахар

-0.59

ſammen

-0.57

 Kino

-0.55

 APPEALS

-0.54

pters

-0.54



-0.54

 שוליים

-0.53

Espèce

-0.53

 soils

-0.53

ftagPool

-0.53

POSITIVE LOGITS

 learning

0.46

learning

0.31

providedIn

0.29

 team

0.27

ISupport

0.26

進

0.26

 Learning

0.26

 academically

0.26

right

0.26

 pribadi

0.26

Activations Density 0.030%

expressions of learning and personal development experiences

preparedness, confidence, learning

No Comments

No Known Activations