INDEX

Explanations

references to training and educational initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 Osbourne

-0.86

 Diocese

-0.83

 Antara

-0.78

 écl

-0.77

 Fencing

-0.76

 spé

-0.74

addFlags

-0.73

 Necklace

-0.73

 KeyCode

-0.73

Edd

-0.72

POSITIVE LOGITS

 training

0.99

 trainings

0.90

 Training

0.87

TRAIN

0.87

 train

0.87

 trainers

0.83

 TRAIN

0.82

Training

0.82

 Train

0.81

 Trainings

0.80

Activations Density 0.047%

references to training and educational initiatives

No Comments

No Known Activations