INDEX

Explanations

references to the concept of "use" and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

laken

-0.80

ValueStyle

-0.76

 Souver

-0.73

 McGregor

-0.71

McM

-0.71

 sympy

-0.71

glEnd

-0.71

 mapStateToProps

-0.69

 Thurston

-0.67

HttpHeaders

-0.66

POSITIVE LOGITS

use

1.61

Use

1.40

use

1.33

Use

1.30

 usage

1.29

USE

1.27

 uses

1.24

uso

1.22

Usage

1.13

 Uses

1.12

Activations Density 0.183%

references to the concept of "use" and its implications

No Comments

No Known Activations