INDEX

Explanations

discussions about experiences and engagements in various contexts

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

before nouns

np_acts-logits-general · gemini-2.0-flash

future events and importance

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 ſta

-0.58

 ProtoMessage

-0.54

ंदीखरीदारी

-0.54

astéroïdes

-0.54

 հղումներ

-0.54

 Khusus

-0.53

 ſte

-0.53

 الاطلاع

-0.53

 houſe

-0.53

Personensuche

-0.52

POSITIVE LOGITS

 career

0.43

 future

0.37

 postre

0.35

 issues

0.35

 scholarship

0.35

MethodName

0.34

Ind

0.34

 struggles

0.33

sti

0.33

 upcoming

0.33

Activations Density 0.149%

discussions about experiences and engagements in various contexts

before nouns

future events and importance

No Comments

No Known Activations