INDEX

Explanations

references to status variables in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

)}(\

-0.91

 Bact

-0.87

 Mirza

-0.79

__':

-0.79

 AppColors

-0.78

 Micah

-0.76

 Coimbra

-0.76

 Médico

-0.75

HEC

-0.72

 Mexicano

-0.72

POSITIVE LOGITS

 STATUS

1.53

 getStatus

1.53

 Status

1.44

STATUS

1.44

 status

1.42

 statuses

1.41

getStatus

1.34

setStatus

1.30

status

1.25

Status

1.23

Activations Density 0.039%

references to status variables in code

No Comments

No Known Activations