INDEX

Explanations

personal pronouns and possessive indicators

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

Negative Logits

 otomatig

-0.71

Tikang

-0.67

 ProtoMessage

-0.67

GEBURTSDATUM

-0.64

MessageOf

-0.62

WebVitals

-0.61

 Exacts

-0.60

 samarbeid

-0.60

calaure

-0.58

protoimpl

-0.57

POSITIVE LOGITS

SuppressMessage

0.60

SequentialGroup

0.58

forName

0.53

KommentareTeilen

0.52

&+

0.52

 htmlFor

0.50

xically

0.50

AddRange

0.50

록

0.50

ParallelGroup

0.50

Activations Density 0.056%

personal pronouns and possessive indicators

No Known Activations