INDEX

Explanations

uses of the word "when" and words that often precede or follow it like "that", "his", "being", and prepositions

oai_token-act-pair · gemini-2.0-flash

Events in time

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 when

-0.63

when

-0.54

When

-0.51

 When

-0.49

 حين

-0.48

 WHEN

-0.46

 that

-0.40

re

-0.38

 quando

-0.37

POSITIVE LOGITS

 GenerationType

0.88

Hentet

0.82

Datuak

0.82

 AssemblyCompany

0.82

bibfield

0.80

ValueStyle

0.79

InSection

0.79

 MaterialApp

0.78

withIdentifier

0.77

 AssemblyTitle

0.77

Activations Density 2.115%

uses of the word "when" and words that often precede or follow it like "that", "his", "being", and prepositions

Events in time

No Comments

No Known Activations