INDEX

Explanations

concepts related to network configurations and their characteristics

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

-0.74

“

-0.70

".

-0.63

-0.62

kon

-0.60

 }^{*}$

-0.60

__["

-0.57

]="

-0.56

+".

-0.56

POSITIVE LOGITS

 itſelf

1.20

 ་་

1.09

ſelf

1.05

 ―――――

1.02

 poffible

0.95

 raiſ

0.95

 myſelf

0.95

Efq

0.94

 iſt

0.93

 Shakspeare

0.93

Activations Density 0.169%

concepts related to network configurations and their characteristics

No Known Activations