INDEX

Explanations

terms related to electrical activity and measurements in neural communications

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

談社

-0.55

AutoresizingMask

-0.52

numerusform

-0.52

 Erben

-0.52

LinkId

-0.51

patch

-0.51

gató

-0.50

SequentialGroup

-0.48

 Patch

-0.47

 Bids

-0.46

POSITIVE LOGITS

ViewFeatures

0.68

 getSystem

0.60

oredCriteria

0.59

 collected

0.59

contentPadding

0.54

isak

0.53

ViewImports

0.53

RequiresApi

0.53

formed

0.53

dafx

0.53

Activations Density 0.012%

terms related to electrical activity and measurements in neural communications

No Comments

No Known Activations