INDEX

Explanations

mathematical notations and operations related to error and data encoding processes

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

 kasarigan

-0.82

 >=",

-0.82

expandindo

-0.80

 ویکی‌پدیای

-0.79

 InputDecoration

-0.78

 transférez

-0.77

:✨

-0.77

QMetaType

-0.77

SourceChecksum

-0.77

AutoScaleMode

-0.75

POSITIVE LOGITS

for

0.48

 ابت

0.45

0.43

 قان

0.43

 بص

0.42

 owned

0.42

 ucap

0.42

Environment

0.41

响

0.41

Activations Density 0.170%

mathematical notations and operations related to error and data encoding processes

No Comments

No Known Activations