INDEX

Explanations

phrases where the author acknowledges what the reader may or may not know

oai_token-act-pair · gemini-2.0-flash

know

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

tagHelperRunner

-1.07

LookAnd

-0.96

Personendaten

-0.81

 estekak

-0.80

Autoritní

-0.80

قایناق‌لار

-0.79

hyrchwyd

-0.79

RenderAtEndOf

-0.79

parsedMessage

-0.78

 lenker

-0.77

POSITIVE LOGITS

 Yesterday

0.51

Yesterday

0.50

кра

0.47

 late

0.47

 Late

0.45

 recently

0.44

Recently

0.43

 recenti

0.43

URLConnection

0.42

recently

0.42

Activations Density 0.994%

phrases where the author acknowledges what the reader may or may not know

know

No Comments

No Known Activations

phrases where the author acknowledges what the reader may or may not know

know

No Comments

No Known Activations