INDEX

Explanations

technical terms and jargon related to computing and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

SVG

-0.46

unnitel

-0.44

vtk

-0.43

 viewers

-0.43

 browsers

-0.42

 viewer

-0.42

Spoljašnje

-0.42

 incontri

-0.42

TintMode

-0.41

JVM

-0.41

POSITIVE LOGITS

 firmware

0.83

 Firmware

0.73

RefNanny

0.70

 Enable

0.69

 Slave

0.68

 voltages

0.66

 Slaves

0.66

 read

0.65

 Modulation

0.64

 slave

0.63

Activations Density 1.282%

technical terms and jargon related to computing and programming

No Comments

No Known Activations