INDEX

Explanations

instances of dialogue or quotes, particularly those indicating problems or opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Diwedd

-0.56

InjectAttribute

-0.55

entraînement

-0.52

preferably

-0.52

цездатний

-0.49

SEGUIR

-0.48

 preferably

-0.48

timely

-0.46

 Olsson

-0.46

purposes

-0.45

POSITIVE LOGITS

Worse

0.53

 Worse

0.52

 worse

0.52

 ब्रेकडाउन

0.48

 peor

0.41

 buruk

0.40

ंदीखरीदारी

0.40

HRESULT

0.40

too

0.38

 poor

0.38

Activations Density 0.945%

instances of dialogue or quotes, particularly those indicating problems or opinions

No Comments

No Known Activations