INDEX

Explanations

words and phrases indicating a sequence of events or actions, often with a sense of continuation or progression toward a later stage or time.

oai_token-act-pair · gemini-2.0-flash

Time/sequencing of events

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

<bos>

-0.76

 initComponents

-0.61

 Cæsar

-0.57

 saites

-0.57

eve

-0.56

XtraEditors

-0.55

ModelSerializer

-0.55

Autoritní

-0.55

 defStyle

-0.55

StructEnd

-0.54

POSITIVE LOGITS

ANTLR

0.50

مصادر

0.49

 usamos

0.48

Geplaatst

0.48

ferent

0.46

/>";

0.46

Таблица

0.45

 namelijk

0.45

haul

0.44

šel

0.44

Activations Density 6.527%

words and phrases indicating a sequence of events or actions, often with a sense of continuation or progression toward a later stage or time.

Time/sequencing of events

No Comments

No Known Activations