INDEX

Explanations

phrases relating to authority and control

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

"The" followed by a noun

np_acts-logits-general · gemini-2.0-flash

the specific noun

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 butterknife

-0.65

 dàng

-0.62

WireFormat

-0.57

 nahilalakip

-0.57

 Acerca

-0.56

 gând

-0.55

 onBackPressed

-0.54

 handelt

-0.54

 pamamagitan

-0.54

 tentativo

-0.54

POSITIVE LOGITS

ThroughAttribute

0.67

ftest

0.64

ModelForm

0.63

 yore

0.62

OF

0.60

queles

0.60

ModelSerializer

0.59

OfDay

0.57

WebControls

0.56

;'>

0.56

Activations Density 0.546%

phrases relating to authority and control

"The" followed by a noun

the specific noun

No Comments

No Known Activations