INDEX

Explanations

geographical or location-based terms

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

Abbreviations and punctuation in technical contexts

np_acts-logits-general · gemini-2.0-flash

0 common polymorphisms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 myſelf

-1.57

ConstraintMaker

-1.43

 itſelf

-1.40

BeginContext

-1.38

 nahilalakip

-1.37

Datuak

-1.35

 themſelves

-1.34

 nakalista

-1.31

 Monfieur

-1.30

bootstrapcdn

-1.29

POSITIVE LOGITS

de

0.67

0.55

0.54

0.53

0.51

0.50

0.48

le

0.47

Activations Density 0.028%

geographical or location-based terms

Abbreviations and punctuation in technical contexts

0 common polymorphisms

No Comments

No Known Activations