INDEX

Explanations

information related to academic publications in the machine learning field

oai_token-act-pair · gemini-2.0-flash

technical documents

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

enumi

-0.69

ſelf

-0.68

 Transvaal

-0.68

 Siamese

-0.66

niająca

-0.66

balleur

-0.64

 ويكيميديا

-0.62

 Presbyter

-0.60

ſelves

-0.60

 gynhyrchwyd

-0.60

POSITIVE LOGITS

ll

0.50

 Segal

0.44

kap

0.42

ongs

0.42

Bre

0.41

 Select

0.41

tero

0.41

par

0.41

og

0.40

à

0.40

Activations Density 2.820%

information related to academic publications in the machine learning field

technical documents

No Known Activations