INDEX

Explanations

symbolic representations of data and references in scientific contexts

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

-0.73

-0.72

-0.69

-0.67

-0.63

 BorderRadius

-0.61

and

-0.60

-0.57

POSITIVE LOGITS

 feroit

1.30

 purpoſe

1.29

 pleaſure

1.27

 myſelf

1.27

 ſta

1.26

 auffi

1.25

 ſtate

1.24

 Houſe

1.24

 itſelf

1.23

 Anſ

1.22

Activations Density 10.860%

symbolic representations of data and references in scientific contexts

No Comments

No Known Activations