INDEX

Explanations

keywords related to programming attributes and functions

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

Hexadecimal values, especially "0x"

np_acts-logits-general · gemini-2.0-flash

hex number parsing

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

pra

-0.43

directive

-0.41

 ISNI

-0.41

WindowConstants

-0.40

>//

-0.39

pra

-0.39

 high

-0.37

 distanciation

-0.37

 zakon

-0.36

POSITIVE LOGITS

ReusableCell

0.73

enderror

0.73

Хьажоргаш

0.73

 resourceCulture

0.68

 AssemblyCulture

0.67

Autoritní

0.67

Vidite

0.66

TestingModule

0.64

CompilerServices

0.64

ώς

0.64

Activations Density 0.132%

keywords related to programming attributes and functions

Hexadecimal values, especially "0x"

hex number parsing

No Comments

No Known Activations