INDEX

Explanations

terms related to transformation processes or requests for updates

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

Text following "the" or "abstract"

np_acts-logits-general · gemini-2.0-flash

abstract and author fields

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-0.75

neſs

-0.70

σθαι

-0.70

 iſt

-0.64

 ſever

-0.61

 itſelf

-0.61

AutoresizingMask

-0.61

 uſed

-0.60

ſelves

-0.59

 Canaria

-0.59

POSITIVE LOGITS

parsedMessage

0.88

 Chwiliwch

0.81

 autorytatywna

0.79

queryInterface

0.79

sizeCache

0.79

principalTable

0.72

LookAnd

0.71

 viewDidLoad

0.70

MigrationBuilder

0.69

 beginnetje

0.69

Activations Density 0.780%

terms related to transformation processes or requests for updates

Text following "the" or "abstract"

abstract and author fields

No Comments

No Known Activations