INDEX

Explanations

comparisons of relative quality, specifically between superior and inferior attributes

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

<i>

-0.77

<em>

-0.70

-0.67

="#"><

-0.64

time

-0.63

Brend

-0.62

…

-0.60

<h2>

-0.60

rungsseite

-0.59

 tạp

-0.59

POSITIVE LOGITS

 Inferior

1.32

 SUPERIOR

1.10

inferior

1.05

 Superior

1.04

superior

1.02

Superior

1.00

 inferior

1.00

 superiori

0.97

 supérieurs

0.94

 supérieure

0.93

Activations Density 0.007%

comparisons of relative quality, specifically between superior and inferior attributes

No Known Activations