INDEX

Explanations

references to validity and valid values

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

expandindo

-0.88

MigrationBuilder

-0.86

 springfox

-0.73

 betweenstory

-0.71

 ComVisible

-0.71

="//

-0.68

 scrapy

-0.67

 Bisch

-0.66

 conferences

-0.66

évaluateur

-0.66

POSITIVE LOGITS

 valid

2.51

valid

2.27

Valid

2.26

 Valid

2.20

VALID

2.12

 VALID

2.04

 válida

1.82

 isValid

1.74

 válido

1.62

isValid

1.62

Activations Density 0.068%

references to validity and valid values

No Comments

No Known Activations