INDEX

Explanations

references to conditions, models, and theories

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

citations and notation

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

UnusedPrivate

-0.62

oredCriteria

-0.60

AddTagHelper

-0.55

IUrlHelper

-0.54

featureID

-0.52

verwijspagina

-0.52

 StringField

-0.52

parsedMessage

-0.51

 initComponents

-0.46

SharedCtor

-0.45

POSITIVE LOGITS

 تضيفلها

0.40

WEBPACK

0.40

spin

0.40

 CanadaChoose

0.39

帖最后由

0.37

prop

0.37

 نف

0.36

izel

0.35

AndEndTag

0.35

meo

0.34

Activations Density 0.306%

references to conditions, models, and theories

citations and notation

No Comments

No Known Activations