INDEX

Explanations

mentions of academic degrees

oai_token-act-pair · gemini-2.0-flash

academic degrees and credentials

np_token-act-pair-logits · gpt-4o-mini

Academic degrees

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 disambiguazione

-0.73

 itſelf

-0.65

 Dipl

-0.65

 raiſ

-0.62

 Diploma

-0.62

 doubtnut

-0.61

Dipl

-0.61

 purpoſe

-0.59

Efq

-0.59

 Deel

-0.59

POSITIVE LOGITS

ClientRect

0.59

 pinulongan

0.55

withIdentifier

0.52

AndroidJUnit

0.52

 Вікі

0.51

Getenv

0.51

 елның

0.49

nesty

0.47

 betweenstory

0.46

 transfieras

0.45

Activations Density 0.941%

mentions of academic degrees

academic degrees and credentials

Academic degrees

No Comments

No Known Activations