INDEX

Explanations

elements related to graphical or data visualization parameters, particularly in the context of figures and diagrams in documents

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

fig and svg references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

transQ

-0.54

WithMany

-0.49

UnknownFieldSet

-0.44

 Schwier

-0.43

InjectMocks

-0.43

AddWithValue

-0.42

 estekak

-0.42

IsMutable

-0.41

AddHtmlAttribute

-0.41

zzleHttp

-0.40

POSITIVE LOGITS

viewBox

0.94

svg

0.89

Svg

0.63

IGraphics

0.56

SVG

0.54

Svg

0.54

 ujednoznacz

0.52

 CreateTagHelper

0.50

lblNewLabel

0.49

svg

0.49

Activations Density 0.004%

elements related to graphical or data visualization parameters, particularly in the context of figures and diagrams in documents

fig and svg references

No Comments

No Known Activations