INDEX

Explanations

copyright and licensing information

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

copyright and rights reserved

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

+#+#

-0.70

complexContent

-0.69

 שוליים

-0.60

曖昧さ回避

-0.60

 Савезне

-0.54

 informée

-0.52

المناصب

-0.52

 ujednoznacz

-0.52

ésultat

-0.52

PreferredItem

-0.52

POSITIVE LOGITS

 copyright

0.41

 ownership

0.41

 owner

0.37

 newOwner

0.36

ャ

0.35

 copyrights

0.35

owned

0.35

 Trust

0.35

righted

0.34

 perten

0.34

Activations Density 0.021%

copyright and licensing information

copyright and rights reserved

No Comments

No Known Activations