INDEX

Explanations

numerical values and related formatting in the text

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

Numbers within parentheses

np_acts-logits-general · gemini-2.0-flash

numbers after punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 initComponents

-0.88

IntoConstraints

-0.80

 forties

-0.73

 Fourth

-0.72

MemoryWarning

-0.70

Espèce

-0.70

 pinulongan

-0.69

 resourceCulture

-0.68

хьтан

-0.67

tvguidetime

-0.65

POSITIVE LOGITS

 nakalista

0.52

0.47

 occidentalis

0.46

́ng

0.42

 rica

0.42

fem

0.41

 Orrell

0.41

 ͜ʖ

0.41

 Schi

0.40

Activations Density 0.434%

numerical values and related formatting in the text

Numbers within parentheses

numbers after punctuation

No Comments

No Known Activations