INDEX

Explanations

instances of the word "secret" and words that frequently occur with it

oai_token-act-pair · gemini-2.0-flash

secrets

np_token-act-pair-logits · gemini-2.0-flash

secret

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

culoskeletal

-0.52

[]:

-0.48

culada

-0.48

BOA

-0.48

gdala

-0.47

 conce

-0.47

penny

-0.46

OSIS

-0.45

ancourt

-0.45

 lingual

-0.45

POSITIVE LOGITS

MLLoader

0.71

RegistryLite

0.64

SharedDtor

0.64

 chimiques

0.61

 فريبيس

0.61

ArrowToggle

0.57

WebMethod

0.57

 ProtoMessage

0.56

WebElementEntity

0.56

fjspx

0.56

Activations Density 1.416%

instances of the word "secret" and words that frequently occur with it

secrets

secret

No Comments

No Known Activations