INDEX

Explanations

references to surfaces and their properties

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

"surface" followed by a related word

np_acts-logits-general · gemini-2.0-flash

surface properties

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

-0.92

 متعلقه

-0.87

IsMutable

-0.87

✨:

-0.81

httphttps

-0.75

ⓧ

-0.72

 محفوظة

-0.70

TagMode

-0.70

 Obrador

-0.69

OGND

-0.69

POSITIVE LOGITS

 tension

0.69

 area

0.56

積

0.55

ficial

0.51

积

0.50

 Tension

0.49

 dwellers

0.47

RequestMethod

0.47

Carson

0.47

 layer

0.47

Activations Density 0.108%

references to surfaces and their properties

"surface" followed by a related word

surface properties

No Comments

No Known Activations