INDEX

Explanations

elements related to formal structure or heading indicators in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Roskov

-1.31

AsUp

-1.23

oredCriteria

-1.17

IntoConstraints

-1.15

Autoritní

-1.14

 ModelExpression

-1.12

ⓧ

-1.09

OGND

-1.03

contentLoaded

-1.02

 betweenstory

-1.00

POSITIVE LOGITS

the

0.68

 general

0.49

↵↵

0.48

 importantly

0.47

 working

0.46

The

0.46

an

0.45

0.43

<em>

0.43

<th>

0.42

Activations Density 0.287%

elements related to formal structure or heading indicators in text

No Comments

No Known Activations