INDEX

Explanations

scientific figures or diagrams within the text

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

odend

-0.59

 onItemClick

-0.58

XmlAccessType

-0.56

igslist

-0.52

arvi

-0.50

ándolos

-0.50

ibald

-0.49

minar

-0.49

 continúas

-0.48

 CreateTagHelper

-0.48

POSITIVE LOGITS

 simplifié

0.72

 Wicidata

0.65

RegressionTest

0.64

SequentialGroup

0.59

 tighter

0.57

 EClass

0.56

 tightened

0.54

 ResourceManager

0.54

 satur

0.52

 informée

0.52

Activations Density 0.002%

scientific figures or diagrams within the text

No Comments

No Known Activations