INDEX

Explanations

numerical data points and identifiers related to datasets or programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

oa̍t

-0.50

StatusOK

-0.49

 inductor

-0.46

ீர

-0.45

 živ

-0.44

 intrigu

-0.44

hbs

-0.43

 esfor

-0.43

 Hül

-0.42

 prioriti

-0.42

POSITIVE LOGITS

مصادر

0.88

ThroughAttribute

0.80

Билгалдахарш

0.79

存于互联网档案馆

0.78

Hochspringen

0.76

IntoConstraints

0.76

χρι

0.74

GOTREF

0.72

afficheront

0.71

makeConstraints

0.70

Activations Density 0.092%

numerical data points and identifiers related to datasets or programming

No Comments

No Known Activations