INDEX

Explanations

references to training and related activities

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

"training"

np_acts-logits-general · gemini-2.0-flash

skill training

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 InputDecoration

-0.60

 Bellow

-0.54

ellido

-0.49

RRect

-0.49

 StatelessWidget

-0.48

 betweenstory

-0.47

oggetto

-0.47

 Clarinet

-0.46

égard

-0.45

 Schall

-0.45

POSITIVE LOGITS

 training

2.05

 Training

1.94

Training

1.93

training

1.85

 TRAINING

1.84

TRAINING

1.77

 trainings

1.59

 trained

1.55

 Trainings

1.45

 Trained

1.44

Activations Density 0.103%

references to training and related activities

"training"

skill training

No Comments

No Known Activations