INDEX

Explanations

words related to file paths, data types, and code configuration

oai_token-act-pair · gemini-2.0-flash

type

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

########.

-0.55

 initComponents

-0.54

 gynhyrchwyd

-0.53

ulemon

-0.51

SpringBootTest

-0.49

 Jackman

-0.49

DockStyle

-0.49

 الحره

-0.49

vyšší

-0.49

ndy

-0.48

POSITIVE LOGITS

__.__

0.44

 发表于

0.44

<?>

0.44

 Instrument

0.43

fra

0.42

':'

0.41

disambiguation

0.41

θεια

0.41

}]

0.40

)_/¯

0.40

Activations Density 19.434%

words related to file paths, data types, and code configuration

type

No Comments

No Known Activations