INDEX

Explanations

data-related terms or concepts, particularly those indicating measurements or values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 estekak

-0.66

complexContent

-0.56

 crystall

-0.56

 Unterschiede

-0.55

slidesPer

-0.55

FontOfSize

-0.54

 ivelany

-0.52

 Voraus

-0.52

 Annahme

-0.52

CodedInputStream

-0.52

POSITIVE LOGITS

 wherever

0.67

 Wherever

0.65

RDP

0.63

WHERE

0.62

uch

0.59

kloped

0.59

urgy

0.58

Asked

0.58

Wherever

0.58

cipar

0.57

Activations Density 0.219%

data-related terms or concepts, particularly those indicating measurements or values

No Comments

No Known Activations