INDEX

Explanations

terms related to properties and attributes in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 purpoſe

-0.99

 raiſ

-0.95

 pleaſure

-0.94

 ſtate

-0.91

 miſ

-0.88

uſ

-0.88

 inſ

-0.87

 myſelf

-0.86

 tranſ

-0.86

 faſt

-0.86

POSITIVE LOGITS

 Properties

1.81

Properties

1.78

 properties

1.77

properties

1.68

 PROPERTIES

1.60

PROPERTIES

1.43

 propiedades

1.01

 propriétés

0.96

Propiedades

0.96

getProperties

0.93

Activations Density 0.109%

terms related to properties and attributes in a technical context

No Comments

No Known Activations