INDEX

Explanations

mathematical or programming constructs that indicate the start of a block or significant transitions in data structure

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

Personendaten

-0.65

arangay

-0.62

 betweenstory

-0.59

Derbyniad

-0.57

abestanden

-0.57

 ब्रेकडाउन

-0.56

delwed

-0.56

 defaultstate

-0.56

 <>",

-0.56

XmlEnum

-0.54

POSITIVE LOGITS

Read

0.43

 ویکی‌پدی

0.40

Показать

0.39

‭

0.38

{:

0.35

ρισσότε

0.35

As

0.34

GTC

0.34

 ErrIntOverflow

0.34

∮

0.34

Activations Density 0.021%

mathematical or programming constructs that indicate the start of a block or significant transitions in data structure

No Comments

No Known Activations