INDEX

Explanations

mathematical notation, specifically terms related to matrices and functions in mathematical expressions

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

</tfoot>

-0.70

 переписи

-0.69

GEBURTS

-0.66

WriteLiteral

-0.65

Derbyniad

-0.63

basicConfig

-0.61

RegressionTest

-0.60

 OFDb

-0.60

setVerticalGroup

-0.58

 rappeler

-0.57

POSITIVE LOGITS

Initializable

0.50

ựa

0.49

alter

0.48

пол

0.47

 alter

0.46

 getopt

0.46

󠁣

0.46

 rospy

0.43

obs

0.43

 чер

0.43

Activations Density 0.015%

mathematical notation, specifically terms related to matrices and functions in mathematical expressions

No Comments

No Known Activations