INDEX

Explanations

references to processes and processing in programming or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

edicated

-0.69

 Pública

-0.64

ſelf

-0.64

 purpoſe

-0.64

 himſelf

-0.63

GRAFIA

-0.63

cycline

-0.63

eleste

-0.61

 Donner

-0.61

 Orrell

-0.61

POSITIVE LOGITS

 processes

0.86

 Processes

0.83

ual

0.79

Processes

0.78

processes

0.71

Tikang

0.67

PROCESS

0.67

 Process

0.66

ess

0.65

 PROCESS

0.62

Activations Density 0.145%

references to processes and processing in programming or technical contexts

No Comments

No Known Activations