INDEX

Explanations

numeric values and specific formatting symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Bourgoin

-0.58

 OFDb

-0.51

########.

-0.46

jenost

-0.45

 Administrativna

-0.43

RTLD

-0.41

Демографія

-0.41

 odeur

-0.40

ut

-0.39

 ausged

-0.39

POSITIVE LOGITS

ConstraintMaker

0.83

Билгалдахарш

0.79

0.78

цездатний

0.76

'),

0.75

BeginContext

0.74

 Paglinawan

0.74

Portail

0.74

بوابة

0.73

 незавершена

0.73

Activations Density 0.516%

numeric values and specific formatting symbols

No Comments

No Known Activations