INDEX

Explanations

mentions of the word "process" and its variations in different contexts

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

fortawesome

-0.49

 nutricional

-0.48

 drapeau

-0.44

 Laurel

-0.44

madison

-0.43

 femininas

-0.43

 whiteColor

-0.43

 psychiat

-0.42

 astronomer

-0.42

 newName

-0.42

POSITIVE LOGITS

 process

1.07

 Process

1.06

process

1.04

 PROCESS

0.91

Process

0.91

 processes

0.88

 Processes

0.85

PROCESS

0.79

 processo

0.78

processes

0.75

Activations Density 0.111%

mentions of the word "process" and its variations in different contexts

No Comments

No Known Activations