INDEX

Explanations

references to specific timelines and events within the current year

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Personendaten

-0.80

 nack

-0.56

 Lagi

-0.54

 Cause

-0.52

 localObject

-0.52

 Diman

-0.49

fuj

-0.48

Gala

-0.48

artan

-0.47

 echar

-0.47

POSITIVE LOGITS

 OFDb

0.78

webElementXpaths

0.74

ValueStyle

0.72

 utafitiHapana

0.71

fhir

0.70

 Wikimedijinoj

0.67

IVEREF

0.64

 typelib

0.62

 становника

0.61

Diweddarwch

0.60

Activations Density 0.138%

references to specific timelines and events within the current year

No Comments

No Known Activations