INDEX

Explanations

mathematical expressions and notation related to functions and sets

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

Tikang

-0.90

RegistryLite

-0.81

Personendaten

-0.69

istani

-0.66

ItemBackground

-0.66

存于互联网档案馆

-0.64

 iNdEx

-0.64

 mData

-0.63

ectors

-0.62

RTRS

-0.62

POSITIVE LOGITS

<eos>

0.57

0.48

OleDb

0.46

0.45

 Drittan

0.45

li

0.44

浅

0.44

TERR

0.43

 bordo

0.43

oursquare

0.41

Activations Density 0.094%

mathematical expressions and notation related to functions and sets

No Comments

No Known Activations