INDEX

Explanations

what appears to be a diverse set of technical or proper nouns and verbs related to documents, people, or actions.

oai_token-act-pair · gemini-2.0-flash

Proc

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ValueStyle

-0.62

localctx

-0.60

[]:

-0.59

 mxArray

-0.57

IVEREF

-0.57

❹

-0.55

INSEE

-0.54

kaido

-0.54

specifier

-0.53

entiary

-0.52

POSITIVE LOGITS

󠁿

0.59

 становника

0.57

 réguli

0.53

 egos

0.50

 виправивши

0.50

]?

0.50

temun

0.49

 Phoen

0.48

 Majefty

0.48

 Cæsar

0.48

Activations Density 13.992%

what appears to be a diverse set of technical or proper nouns and verbs related to documents, people, or actions.

Proc

No Comments

No Known Activations