INDEX

Explanations

references to cross-national studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

IVEREF

-0.75

RegistryLite

-0.75

ngdoc

-0.69

 AssemblyProduct

-0.67

انيف

-0.66

AccessorTable

-0.64

 Paused

-0.64

 مشين

-0.62

 Lehre

-0.62

 parlato

-0.62

POSITIVE LOGITS

 cross

5.12

 Cross

4.63

cross

4.61

Cross

4.53

 CROSS

4.21

CROSS

3.94

 crosses

3.38

 crossed

3.10

 cros

2.79

 crossing

2.75

Activations Density 0.072%

references to cross-national studies

No Comments

No Known Activations