INDEX

Explanations

reference markers and punctuation in a programming or structured data context

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

Characters surrounded by parentheses

np_acts-logits-general · gemini-2.0-flash

section numbers and codes

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

 Roskov

-0.92

 aapt

-0.89

ImageContext

-0.86

Vidite

-0.84

ьаж

-0.83

 مشين

-0.82

GEBURTS

-0.81

ItemBackground

-0.81

 pulumi

-0.80

httphttps

-0.80

POSITIVE LOGITS

pe

0.48

0.45

0.44

 veľa

0.43

Me

0.43

Me

0.42

関する

0.42

แ

0.42

ve

0.41

Activations Density 0.582%

reference markers and punctuation in a programming or structured data context

Characters surrounded by parentheses

section numbers and codes

No Comments

No Known Activations