INDEX

Explanations

terms relating to devices and their functions

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

 nakalista

-0.67

complexContent

-0.63

InjectAttribute

-0.54

kül

-0.50

idenav

-0.48

 calyx

-0.48

期刊论文

-0.47

 pres

-0.46

 obel

-0.46

onal

-0.46

POSITIVE LOGITS

 protoimpl

0.73

MessageTagHelper

0.67

 للمعارف

0.63

 Вікі

0.61

Probably

0.60

QMetaType

0.60

Somehow

0.59

Lähteet

0.59

 مشين

0.58

tlement

0.58

Activations Density 1.027%

terms relating to devices and their functions

No Comments

No Known Activations