INDEX

Explanations

references to spaces in a mathematical or 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

Negative Logits

 Monfieur

-1.05

 pleaſure

-0.98

ſelves

-0.96

 themſelves

-0.96

OGND

-0.95

 Majefty

-0.95

 havaianas

-0.94

 hydrauli

-0.94

 Chriftian

-0.92

 myſelf

-0.91

POSITIVE LOGITS

 space

1.71

 Space

1.66

 spaces

1.66

 SPACE

1.62

 Spaces

1.61

Spaces

1.57

space

1.52

Space

1.52

SPACE

1.52

spaces

1.46

Activations Density 0.238%

references to spaces in a mathematical or programming context

No Known Activations