INDEX

Explanations

mentions of supplemental or additional concepts

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

in addition to

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

ModelAndView

-0.50

httphttps

-0.49

plier

-0.49

erover

-0.46

wär

-0.46

gonic

-0.45

titleMargin

-0.45

icali

-0.44

 BitmapFactory

-0.44

MessageTagHelper

-0.44

POSITIVE LOGITS

DebuggerNonUser

0.40

EDEFAULT

0.36

EndGlobalSection

0.35

 odkazy

0.33

Parcelize

0.30

zupeł

0.28

Étymologie

0.28

 complément

0.28

uillez

0.28

 задержа

0.28

Activations Density 0.079%

mentions of supplemental or additional concepts

in addition to

No Comments

No Known Activations