INDEX

Explanations

the beginning of new sections or topics in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

<bos>

-1.06

 estadounid

-0.44

 queſta

-0.39

 indígen

-0.37

 ſei

-0.37

ρυ

-0.37

 increí

-0.36

úb

-0.36

 mauva

-0.35

########.

-0.35

POSITIVE LOGITS

^(@)

0.35

drawal

0.34

ficulty

0.32

csolódó

0.31

>\<^

0.30

uests

0.29

ideration

0.29

[],

0.29

ignty

0.29

%\]

0.28

Activations Density 42.632%

the beginning of new sections or topics in a text

No Comments

No Known Activations