INDEX

Explanations

terms related to everyday activities and routines in daily life

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

and

-0.47

 research

-0.46

che

-0.44

 model

-0.44

気で

-0.43

ex

-0.43

वान

-0.43

↵

-0.42

Ben

-0.41

POSITIVE LOGITS

 disambiguazione

1.14

 Monfieur

1.04

 quotidien

1.02

WebVitals

1.01

 myſelf

1.00

everyday

0.97

 Theſe

0.96

 everyday

0.95

 Everyday

0.94

 quotidi

0.94

Activations Density 0.111%

terms related to everyday activities and routines in daily life

No Comments

No Known Activations