INDEX

Explanations

terms related to electronic devices and their functionality

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

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

+#+

-0.65

سطس

-0.60

 препратки

-0.58

SafeMath

-0.56

\}_{

-0.54

TagMode

-0.54

Bezier

-0.52

bindParam

-0.51

 Taktlose

-0.51

happens

-0.50

POSITIVE LOGITS

 installed

1.17

 mounted

1.03

 Installed

0.91

 instalada

0.90

installed

0.88

 operated

0.87

 instalado

0.86

 installation

0.85

 setup

0.83

 equipped

0.81

Activations Density 1.068%

terms related to electronic devices and their functionality

No Comments

No Known Activations