INDEX

Explanations

references to class types and hierarchies in programming or classification contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 uſed

-1.00

 poffible

-1.00

 neceffary

-0.96

 withal

-0.94

 poffe

-0.92

 Monfieur

-0.88

 juſt

-0.87

 pleaſure

-0.86

 Reſ

-0.85

 ſeveral

-0.83

POSITIVE LOGITS

 Class

1.72

 class

1.61

 CLASS

1.55

 classes

1.54

Class

1.47

class

1.46

classnames

1.37

 Classes

1.36

CLASS

1.36

classes

1.30

Activations Density 0.086%

references to class types and hierarchies in programming or classification contexts

No Comments

No Known Activations