INDEX

Explanations

words or short phrases indicating a process or experiment is being performed or described

oai_token-act-pair · gemini-2.0-flash

called/termed

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 called

-0.88

called

-0.71

 Called

-0.68

 llamado

-0.65

 CALLED

-0.62

 называ

-0.60

Called

-0.58

 chiamato

-0.58

 llamada

-0.56

叫做

-0.56

POSITIVE LOGITS

GEBURTSDATUM

1.14

 للمعارف

0.96

Personensuche

0.90

IntoConstraints

0.85

migrationBuilder

0.85

Portale

0.84

 BorderRadius

0.83

 виправивши

0.81

rungsseite

0.80

:✨

0.79

Activations Density 31.611%

words or short phrases indicating a process or experiment is being performed or described

called/termed

No Comments

No Known Activations