INDEX

Explanations

entries that signal the beginning of a new section or topic 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 @ 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

endphp

-0.99

 صوتيه

-0.96

mybatisplus

-0.86

 vPvB

-0.86

Glej

-0.83

 betweenstory

-0.83

InjectAttribute

-0.81

initializeApp

-0.81

 FetchType

-0.80

nodoc

-0.79

POSITIVE LOGITS

<strong>

2.04

<b>

1.45

<em>

1.40

<u>

1.06

</strong>

1.02

//

0.94

<h2>

0.93

“

0.83

<i>

0.82

<h3>

0.80

Activations Density 0.004%

entries that signal the beginning of a new section or topic in a text

No Comments

No Known Activations