INDEX

Explanations

HTML elements within the document

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

`</body> </html>` sequences

np_acts-logits-general · gemini-2.0-flash

html document endings

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

 EconPapers

-0.79

はじめに

-0.69

المناصب

-0.65

AddTagHelper

-0.61

RenderAtEndOf

-0.61

enumi

-0.59

ectoria

-0.56

 Италијани

-0.56

Życiorys

-0.56

 Administrativna

-0.55

POSITIVE LOGITS

ApplicationTests

0.53

expandindo

0.50

<eos>

0.49

MLLoader

0.49

ană

0.48

ellees

0.48

=<?

0.47

ToTop

0.47

 forever

0.47

 footer

0.47

Activations Density 0.065%

HTML elements within the document

`</body> </html>` sequences

html document endings

No Comments

No Known Activations