INDEX

Explanations

mentions of classes in programming context

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 neceffary

-0.97

umumkan

-0.96

 uſed

-0.96

 raiſ

-0.95

 withal

-0.92

 poffe

-0.91

 poffible

-0.91

 pleaſure

-0.91

 Monfieur

-0.90

 themſelves

-0.89

POSITIVE LOGITS

 Class

1.77

 class

1.64

 CLASS

1.60

class

1.56

 classes

1.55

Class

1.54

classnames

1.47

CLASS

1.45

 Classes

1.43

classes

1.38

Activations Density 0.316%

mentions of classes in programming context

No Comments

No Known Activations