INDEX

Explanations

dialogue that expresses authority and admonishment

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

Text following quotes

np_acts-logits-general · gemini-2.0-flash

start of sentences or phrases

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

########.

-0.53

fjspx

-0.51

PasswordEncoder

-0.50

ngOnInit

-0.48

TryGetValue

-0.47

 referrerpolicy

-0.46

那天

-0.45

didSet

-0.44

 pers

-0.42

Smiling

-0.42

POSITIVE LOGITS

afficheront

0.78

DockStyle

0.67

Coordonnées

0.66

qrst

0.64

RegressionTest

0.64

 CreateTagHelper

0.64

Personensuche

0.63

webElement

0.62

Geplaatst

0.61

rrggbb

0.58

Activations Density 0.125%

dialogue that expresses authority and admonishment

Text following quotes

start of sentences or phrases

No Comments

No Known Activations