INDEX

Explanations

phrases indicating conclusions or structured responses

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

Numbers enclosed in parentheses

np_acts-logits-general · gemini-2.0-flash

enumerated item 1

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 AssemblyProduct

-0.78

 AssemblyCulture

-0.74

 незавершена

-0.69

Personendaten

-0.64

 мәкал

-0.61

 Мексичка

-0.61

 חיצוניים

-0.60

Portály

-0.57

下载附件

-0.55

Manbalar

-0.54

POSITIVE LOGITS

0.84

⒈

0.72

❶

0.71

①

0.68

VersionUID

0.66

۱

0.66

 pertama

0.63

①

0.63

enumerate

0.62

１

0.61

Activations Density 0.229%

phrases indicating conclusions or structured responses

Numbers enclosed in parentheses

enumerated item 1

No Comments

No Known Activations