INDEX

Explanations

words related to brands, media, and comic books

oai_token-act-pair · gemini-2.0-flash

proper nouns, names and titles

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

Name or title of object

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

SharedCtor

-0.43

 virke

-0.42

Hochspringen

-0.41

 marrom

-0.40

 kjem

-0.39

Views

-0.38

aarrggbb

-0.37

nię

-0.36

rů

-0.36

 volantes

-0.36

POSITIVE LOGITS

UnknownFieldSet

1.00

ViewImports

0.89

MLLoader

0.79

 kasarigan

0.78

TypedDataSet

0.77

contentLoaded

0.75

 gynhyrchwyd

0.75

httphttps

0.73

SupportActionBar

0.72

 jsPsych

0.71

Activations Density 1.235%

words related to brands, media, and comic books

proper nouns, names and titles

Name or title of object

No Comments

No Known Activations