INDEX

Explanations

references to various forms and aspects of training

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

Edd

-0.83

 Osbourne

-0.83

 Antara

-0.82

 KeyCode

-0.79

 écl

-0.75

 Diocese

-0.75

 Automobiles

-0.72

poc

-0.71

 Sedgwick

-0.71

 Necklace

-0.70

POSITIVE LOGITS

 training

1.36

 Training

1.14

 trainings

1.12

Training

1.08

training

1.08

 train

1.05

 trainers

1.04

 TRAINING

1.00

 Trainings

0.99

TRAINING

0.99

Activations Density 0.069%

references to various forms and aspects of training

No Comments

No Known Activations