INDEX

Explanations

mathematical symbols and expressions related to functions and mappings

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

NewUrlParser

-0.63

inear

-0.55

 jScrollPane

-0.55

Superintendent

-0.54

(&:

-0.54

Ingestion

-0.53

 digress

-0.53

पया

-0.53

Sklici

-0.53

 Weltkrieg

-0.52

POSITIVE LOGITS

 separately

0.55

toBeTruthy

0.48

cupa

0.48

 Raffa

0.47

GIVEREF

0.46

 activa

0.45

 jossa

0.45

-------------</

0.44

 locul

0.44

 susun

0.44

Activations Density 0.044%

mathematical symbols and expressions related to functions and mappings

No Comments

No Known Activations