INDEX

Explanations

programming-related concepts and functions

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

Code snippets and programming-related terms

np_acts-logits-general · gemini-2.0-flash

sprite creation and properties

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

-0.84

-0.82

-0.80

the

-0.78

so

-0.72

an

-0.71

-0.70

in

-0.70

is

-0.69

-0.68

POSITIVE LOGITS

 myſelf

1.42

 pleaſure

1.34

 تضيفلها

1.33

 Anſ

1.32

 itſelf

1.32

 CreateTagHelper

1.30

 Monfieur

1.30

 purpoſe

1.29

ſelves

1.27

脚注の使い方

1.26

Activations Density 0.148%

programming-related concepts and functions

Code snippets and programming-related terms

sprite creation and properties

No Comments

No Known Activations