INDEX

Explanations

biological and demographic classifications

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

parenthetical phrases; abbreviations

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

tvguidetime

-0.42

[…]

-0.32

...",

-0.32

 Grä

-0.32

...

-0.32

 ویکی‌پدیای

-0.31

…

-0.31

..."

-0.31

{...

-0.30

NewUrlParser

-0.30

POSITIVE LOGITS

DockStyle

0.64

 Wiktionnaire

0.63

 FetchType

0.61

 '\\;'

0.57

Aholisi

0.57

 myſelf

0.54

postIndex

0.52

 الحره

0.51

ConstraintMaker

0.50

IsContent

0.50

Activations Density 0.155%

biological and demographic classifications

parenthetical phrases; abbreviations

No Comments

No Known Activations