INDEX

Explanations

SQL code snippets and database related commands or references in formal settings

oai_token-act-pair · gemini-2.0-flash

see make create

np_max-act · gemini-2.0-flash

say "uppercase"

np_max-act-logits · gpt-5-mini

Triggered by @chenshw0109

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 GETS

-1.32

 INCLUDES

-1.24

 SEEN

-1.19

 SAYS

-1.18

 MEANS

-1.18

 SAID

-1.16

 COMES

-1.15

 WERE

-1.13

 WENT

-1.13

 INCLUDE

-1.13

POSITIVE LOGITS

 have

0.79

 make

0.72

put

0.70

 will

0.69

we

0.68

has

0.66

 take

0.65

is

0.64

may

0.63

can

0.61

Activations Density 4.411%

SQL code snippets and database related commands or references in formal settings

see make create

say "uppercase"

No Known Activations