INDEX

Explanations

elements and structure within code or data representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

setVerticalGroup

-0.86

GEBURTSDATUM

-0.82

󠁴

-0.79

SourceChecksum

-0.75

 ***!

-0.72

 beginnetje

-0.70

 kaarangay

-0.69

 '\\;'

-0.69

ніципалі

-0.68

archiviato

-0.66

POSITIVE LOGITS

smh

0.48

 dest

0.46

XmlElement

0.46

MCH

0.42

 menge

0.42

hor

0.42

illary

0.41

shtml

0.41

iense

0.41

INET

0.41

Activations Density 0.106%

elements and structure within code or data representations

No Comments

No Known Activations