INDEX

Explanations

mention of the name "Ed" or variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

VersionUID

-0.64

 怎样

-0.64

Gambas

-0.61

 tartalomajánló

-0.56

BASELINE

-0.56

 AssemblyVersion

-0.55

CompleteListener

-0.53

 متعلقه

-0.53

SuspendLayout

-0.50

Strip

-0.49

POSITIVE LOGITS

Ed

0.73

ed

0.71

ⓧ

0.70

Ed

0.68

Geplaatst

0.65

gerton

0.65

ouard

0.63

 Paglinawan

0.63

war

0.61

Edw

0.61

Activations Density 0.100%

mention of the name "Ed" or variations of it

No Comments

No Known Activations