INDEX

Explanations

words related to information technology

oai_token-act-pair · gemini-2.0-flash

Companies

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

rungsseite

-0.79

Inc

-0.78

Inc

-0.71

tonsoft

-0.63

 cref

-0.63

 ſtate

-0.62

INC

-0.59

inc

-0.58

 himſelf

-0.57

 psycopg

-0.57

POSITIVE LOGITS

 Private

0.73

Private

0.64

 PRIVATE

0.61

PRIVATE

0.59

 private

0.58

private

0.54

CopyWith

0.54

وفاته

0.49

 OMITBAD

0.49

 Préférences

0.48

Activations Density 0.462%

words related to information technology

Companies

No Comments

No Known Activations