INDEX

Explanations

concepts related to introspection and personal understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

httphttps

-0.63

MLLoader

-0.62

DrawerToggle

-0.61

 Diarsipkan

-0.59

 GenerationType

-0.58

ruptedException

-0.56

 Kela

-0.55

XmlAccessType

-0.54

'):

-0.53

pede

-0.53

POSITIVE LOGITS

تقاوى

0.75

 <>",

0.65

jsii

0.60

 AssemblyCulture

0.60

withIdentifier

0.58

Tikang

0.55

ResumeLayout

0.53

+:+

0.51

LookAnd

0.51

ۇ

0.51

Activations Density 0.299%

concepts related to introspection and personal understanding

No Comments

No Known Activations