INDEX

Explanations

symbols and mathematical notation often associated with complex expressions or equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ThroughAttribute

-0.76

 betweenstory

-0.73

AutoScale

-0.66

parsedMessage

-0.60

GEBURTS

-0.58

Архівовано

-0.57

GEBURTSDATUM

-0.57

 ويكيپيديا

-0.55

❹

-0.53

brates

-0.52

POSITIVE LOGITS

 שוליים

0.61

 InputDecoration

0.58

//

0.56

 lät

0.56

UnifiedTopology

0.54

 isInitialized

0.52

ztő

0.51

 autorytatywna

0.49

htë

0.48

actéristi

0.48

Activations Density 0.652%

symbols and mathematical notation often associated with complex expressions or equations

No Comments

No Known Activations