INDEX

Explanations

strong numerical values or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 صوتيه

-0.90

 estekak

-0.78

 ویکی‌پدیا

-0.77

 Walkover

-0.76

 esternos

-0.73

 الحره

-0.73

 للاسماء

-0.72

BeginContext

-0.70

RegistryLite

-0.68

存于互联网档案馆

-0.67

POSITIVE LOGITS

tax

1.13

Tax

1.02

Tax

1.00

tax

0.97

 taxes

0.97

 taxation

0.90

TAX

0.88

Taxes

0.86

 taxed

0.84

 Taxation

0.84

Activations Density 0.304%

strong numerical values or measurements

No Comments

No Known Activations