INDEX

Explanations

comparative phrases that express preference or alternatives

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

verständlich

-0.75

ModelSerializer

-0.72

Rik

-0.70

 protoimpl

-0.70

Oli

-0.69

POSIX

-0.69

 dataGridView

-0.69

 AttributeSet

-0.69

Bil

-0.68

modelBuilder

-0.68

POSITIVE LOGITS

 Rather

1.36

Rather

1.28

 Instead

1.27

uttosto

1.25

Instead

1.23

 rather

1.22

instead

1.18

 instead

1.16

rather

1.13

 plutôt

0.93

Activations Density 0.081%

comparative phrases that express preference or alternatives

No Comments

No Known Activations