INDEX

Explanations

instances of formatting or visual elements in the text

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

Preceding tokens before certain words

np_acts-logits-general · gemini-2.0-flash

academic or technical terms

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

 AssemblyCulture

-0.89

Xna

-0.72

migrationBuilder

-0.72

 <>",

-0.70

RuleContext

-0.69

MLLoader

-0.68

TestingModule

-0.68

>{@

-0.66

 ویکی‌پدیای

-0.64

 <=",

-0.64

POSITIVE LOGITS

“...

0.47

0.45

0.44

About

0.44

...

0.44

Aspect

0.43

The

0.43

0.42

 geçen

0.42

Activations Density 0.073%

instances of formatting or visual elements in the text

Preceding tokens before certain words

academic or technical terms

No Comments

No Known Activations