INDEX

Explanations

mathematical expressions and variables related to function definitions and calculations

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

tagHelper

-0.52

 CommandType

-0.52

ruch

-0.52

 akcji

-0.50

 ilustracji

-0.49

pointments

-0.47

 snippetHide

-0.47

 useContext

-0.46

 sprawy

-0.46

 Matta

-0.46

POSITIVE LOGITS

 subtracting

0.53

]-'

0.52

Subtract

0.50

setminus

0.48

subtract

0.48

 subtract

0.48

∖

0.45

 Subtract

0.44

>−</

0.40

−

0.40

Activations Density 0.957%

mathematical expressions and variables related to function definitions and calculations

No Comments

No Known Activations