INDEX

Explanations

references to organizational changes and modifications related to entities or terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ükemmel

-0.58

WritableDatabase

-0.56

 malha

-0.51

duplicate

-0.51

leşti

-0.48

tså

-0.47

ølge

-0.47

 zvlá

-0.47

pfung

-0.47

enfance

-0.47

POSITIVE LOGITS

 الرياضيه

0.68

ScopeManager

0.64

 typelib

0.62

 newOwner

0.59

 stap

0.56

ingale

0.55

useState

0.54

FunctionFlags

0.54

 memoized

0.54

 Changing

0.54

Activations Density 0.528%

references to organizational changes and modifications related to entities or terms

No Comments

No Known Activations