INDEX

Explanations

references to scripting or programming tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

atação

-0.51

FromFile

-0.49

leine

-0.48

chism

-0.48

 Aufla

-0.48

 απα

-0.48

etzt

-0.48

맺

-0.48

 skolen

-0.47

mappedBy

-0.46

POSITIVE LOGITS

 directory

1.51

 folder

1.49

 folders

1.28

folder

1.27

 directories

1.25

 Folder

1.20

dir

1.18

directory

1.16

dir

1.16

Folder

1.16

Activations Density 0.624%

references to scripting or programming tasks

No Comments

No Known Activations