INDEX

Explanations

notes or annotations within the text

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

 endblock

-0.56

 Sitten

-0.51

picuous

-0.47

devel

-0.46

 Perrin

-0.46

 Einzelnen

-0.44

 Италијани

-0.44

gameObject

-0.44

etsu

-0.43

 SEDS

-0.43

POSITIVE LOGITS

HasAnnotation

0.75

 Wicidata

0.66

 تضيفلها

0.65

GeoNames

0.64

 مؤرشف

0.63

StoryboardSegue

0.63

ricians

0.62

 Paglinawan

0.60

Override

0.58

override

0.58

Activations Density 0.240%

notes or annotations within the text

No Comments

No Known Activations