INDEX

Explanations

symbols and formatting used in visual or mathematical contexts

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

Technical or numerical expressions

np_acts-logits-general · gemini-2.0-flash

numbers and specific technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 bArr

-0.53

AsUp

-0.49

таратура

-0.48

mí

-0.48

 ActivatedRoute

-0.47

Glej

-0.47

více

-0.46

Hew

-0.45

 grund

-0.44

ology

-0.44

POSITIVE LOGITS

 BoxFit

0.75

 disambiguazione

0.62

 consultato

0.61

tvguidetime

0.61

Revenir

0.59

IBOutlet

0.59

 AssemblyTitle

0.59

IntoConstraints

0.55

]._

0.55

GeoNames

0.55

Activations Density 0.211%

symbols and formatting used in visual or mathematical contexts

Technical or numerical expressions

numbers and specific technical terms

No Comments

No Known Activations