INDEX

Explanations

references to points or locations indicated by "at"

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

-0.59

↵

-0.55

...

-0.55

総

-0.51

早

-0.49

—

-0.49

--

-0.48

-0.47

-0.46

//

-0.46

POSITIVE LOGITS

 كومونز

1.13

 EconPapers

1.13

Datuak

1.12

 autorytatywna

1.04

Geplaatst

1.02

 Wicidata

1.02

MLLoader

1.01

 snippetHide

0.98

 المعيارى

0.97

 propOrder

0.97

Activations Density 0.006%

references to points or locations indicated by "at"

No Comments

No Known Activations

references to points or locations indicated by "at"

No Comments

No Known Activations