INDEX

Explanations

HTML and formatting tags in a document

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

HTML paragraph tag

np_acts-logits-general · gemini-2.0-flash

p followed by > or class

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RenderAtEndOf

-0.79

хьтан

-0.74

-0.72

webElementXpaths

-0.70

 Wikimedijinoj

-0.69

 lenker

-0.69

expandindo

-0.67

LLocation

-0.65

$_['

-0.64

ьаж

-0.64

POSITIVE LOGITS

didSet

0.57

0.51

 Italie

0.48

0.46

 Italij

0.46

 Infórmanos

0.46

InitStruct

0.45

setLayoutParams

0.45

ASX

0.44

 قلي

0.44

Activations Density 0.068%

HTML and formatting tags in a document

HTML paragraph tag

p followed by > or class

No Comments

No Known Activations