INDEX

Explanations

code structures and functions related to data processing and interaction with models in a programming context

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

Code snippets or programming-related content

np_acts-logits-general · gemini-2.0-flash

hexadecimal numbers

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

 disambiguazione

-0.80

ConstraintMaker

-0.69

 AssemblyCulture

-0.69

 himo

-0.69

featureID

-0.64

ViewFeatures

-0.64

 typeof

-0.61

 QLabel

-0.61

POSITIVE LOGITS

//

0.53

 ویکی‌پدیا

0.50

hir

0.50

 infra

0.46

 offline

0.46

 Picchu

0.45

 transferência

0.45

///**

0.44

 Sinus

0.44

ittäin

0.43

Activations Density 0.023%

code structures and functions related to data processing and interaction with models in a programming context

Code snippets or programming-related content

hexadecimal numbers

No Comments

No Known Activations