INDEX

Explanations

elements related to processes and actions in technical or structured contexts

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

Tokens followed by "process" or similar

np_acts-logits-general · gemini-2.0-flash

describing a process

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 surla

-0.62

 HasFactory

-0.56

ichord

-0.53

RTLR

-0.53

Distribuzione

-0.52

})();

-0.50

########.

-0.50

 pinulongan

-0.49

ercito

-0.48

 GenerationType

-0.48

POSITIVE LOGITS

 process

4.23

process

3.75

 Process

3.53

Process

3.40

 PROCESS

3.27

 processes

3.20

 proceso

3.01

 processus

2.92

 processo

2.89

PROCESS

2.88

Activations Density 0.606%

elements related to processes and actions in technical or structured contexts

Tokens followed by "process" or similar

describing a process

No Comments

No Known Activations