INDEX

Explanations

sections labeled as "abstract" in academic papers

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

Text found immediately before "abstract"

np_acts-logits-general · gemini-2.0-flash

paper abstract

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

MigrationBuilder

-0.94

UserScript

-0.80

ImageContext

-0.77

ValueStyle

-0.75

expandindo

-0.73

CodeAttribute

-0.70

StoryboardSegue

-0.70

ollectionView

-0.69

 Wikimedijinoj

-0.69

>-->

-0.69

POSITIVE LOGITS

0.56

ab

0.53

abstract

0.52

 about

0.44

α

0.43

Ab

0.39

0.38

…

0.38

rai

0.38

 доста

0.38

Activations Density 0.079%

sections labeled as "abstract" in academic papers

Text found immediately before "abstract"

paper abstract

No Comments

No Known Activations