INDEX

Explanations

technical terms related to interrupts and data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ftagPool

-0.60

ThemeOverlay

-0.57

 autorytatywna

-0.56

География

-0.55

scrapy

-0.54

 ويكيميديا

-0.54

WEBPACK

-0.53

 abstrait

-0.52

WebElementEntity

-0.51

 visitation

-0.50

POSITIVE LOGITS

 calibration

0.69

 Enable

0.64

ReadByte

0.63

 firmware

0.62

 read

0.62

 enable

0.60

 Calibration

0.60

 calibrate

0.59

Led

0.59

 Setting

0.58

Activations Density 1.062%

technical terms related to interrupts and data processing

No Comments

No Known Activations