INDEX

Explanations

numerical values or structured data relevant to specific metrics or measurements

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

months

np_acts-logits-general · gemini-2.0-flash

dates and international greetings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Efq

-0.70

 ModelExpression

-0.67

 andato

-0.65

iprot

-0.62

$_"

-0.62

}}$\\

-0.58

 riuscito

-0.58

%");

-0.57

 ſeveral

-0.57

 Gorb

-0.56

POSITIVE LOGITS

 SwitchCompat

0.73

AddTagHelper

0.66

ミナル

0.59

Tembelea

0.53

स्तु

0.52

 surla

0.51

coste

0.51

IMPORTED

0.49

Saying

0.48

 Abschied

0.48

Activations Density 0.046%

numerical values or structured data relevant to specific metrics or measurements

months

dates and international greetings

No Comments

No Known Activations