INDEX

Explanations

HTML tags and image attributes within a web document

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

Followed by "alt=" within image tags

np_acts-logits-general · gemini-2.0-flash

image alt attributes

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

yaz

-0.56

åt

-0.52

 Capital

-0.50

 otwar

-0.50

 économies

-0.49

Geometry

-0.47

 geometry

-0.47

 pembun

-0.46

apollo

-0.46

pen

-0.45

POSITIVE LOGITS

SizeMode

0.75

ImageContext

0.70

AnchorStyles

0.67

ContextHolder

0.67

TypedDataSet

0.64

principalTable

0.62

 UIImageView

0.60

WebServlet

0.58

 BoxFit

0.58

 AssemblyProduct

0.58

Activations Density 0.150%

HTML tags and image attributes within a web document

Followed by "alt=" within image tags

image alt attributes

No Comments

No Known Activations