INDEX

Explanations

references to "pro" as it relates to professional-grade tools or features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Theſe

-0.96

 Beſ

-0.83

Efq

-0.81

 Monfieur

-0.77

 ་་

-0.76

 SPDX

-0.72

 encu

-0.72

ſelf

-0.72

BibitemShut

-0.72

 doubtnut

-0.72

POSITIVE LOGITS

pro

3.45

Pro

3.34

Pro

3.25

pro

3.04

PRO

2.59

PRO

2.50

プロ

1.78

 pros

1.70

 Pros

1.53

 프로

1.52

Activations Density 0.068%

references to "pro" as it relates to professional-grade tools or features

No Comments

No Known Activations