INDEX

Explanations

specific terms and phrases relating to definitions or classifications within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

setCharacter

-0.35

expandindo

-0.34

SOCKET

-0.32

 olvido

-0.32

таратура

-0.31

객

-0.30

 nimic

-0.29

gráfica

-0.29

-0.28

 acusa

-0.28

POSITIVE LOGITS

.*")]

0.67

 Phrases

0.64

 phrases

0.63

出版年

0.59

 phrase

0.58

rrggbb

0.57

 '\\;'

0.57

RenderAtEndOf

0.56

phrase

0.55

YourGuide

0.54

Activations Density 0.321%

specific terms and phrases relating to definitions or classifications within a text

No Comments

No Known Activations