INDEX

Explanations

words related to usage and applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

McM

-0.84

 MacGregor

-0.78

 McGregor

-0.74

 McCarty

-0.71

 unforgettable

-0.70

 McFar

-0.70

 Colman

-0.69

 unfair

-0.68

HttpHeaders

-0.67

MemoryWarning

-0.67

POSITIVE LOGITS

use

1.43

use

1.42

Use

1.22

Use

1.21

USE

1.09

uso

1.09

Uso

1.08

USE

1.07

 uses

1.01

Uso

0.99

Activations Density 0.120%

words related to usage and applications

No Comments

No Known Activations