INDEX

Explanations

references to specific libraries, packages, or statistical functions in programming contexts

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

hexadecimal and technical terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

<strong>

-0.46

-0.40

Dr

-0.39

-0.37

The

-0.36

 bowiem

-0.35

<b>

-0.35

So

-0.35

POSITIVE LOGITS

 autorytatywna

1.00

 الحره

0.89

TagMode

0.88

 kasarigan

0.85

 Administrativna

0.85

+#+#

0.85

 للمعارف

0.83

出版年

0.82

 otomatig

0.80

Datuak

0.76

Activations Density 0.023%

references to specific libraries, packages, or statistical functions in programming contexts

hexadecimal and technical terms

No Comments

No Known Activations