INDEX

Explanations

punctuation marks and numerical representations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 moreover

-0.88

 furthermore

-0.84

 Asimismo

-0.83

withstanding

-0.82

apimachinery

-0.80

Примеча

-0.79

Furthermore

-0.78

 Additionally

-0.78

BASEPATH

-0.78

 additionally

-0.78

POSITIVE LOGITS

 They

0.73

The

0.71

He

0.64

They

0.61

0.59

We

0.59

The

0.58

 There

0.56

0.53

Activations Density 0.414%

punctuation marks and numerical representations

No Comments

No Known Activations