INDEX

Explanations

references to quality in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

rrggbb

-0.59

 spake

-0.56

 DialogInterface

-0.56

Schedulers

-0.53

 DECLARATION

-0.51

 NavController

-0.51

 traduit

-0.51

 dudas

-0.51

 pulsar

-0.49

 Mammals

-0.49

POSITIVE LOGITS

 quality

4.78

quality

4.26

 Quality

4.16

Quality

4.13

 QUALITY

3.91

QUALITY

3.65

 calidad

3.24

 qualité

3.22

 qualidade

3.17

 kwaliteit

3.02

Activations Density 0.068%

references to quality in various contexts

No Comments

No Known Activations