INDEX

Explanations

terms related to learning and school

oai_token-act-pair · gemini-2.0-flash

learning

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 passés

-0.65

 monoxide

-0.59

 Sociales

-0.56

adpleegd

-0.56

IsMutable

-0.54

ieee

-0.54

 galaxia

-0.54

entrale

-0.54

 livestream

-0.54

guenos

-0.53

POSITIVE LOGITS

createClass

0.50

OpenHelper

0.50

้อมูล

0.48

 cost

0.48

AlterField

0.47

XmlType

0.46

ParseException

0.43

apunov

0.43

 turn

0.43

ignez

0.43

Activations Density 2.633%

terms related to learning and school

learning

No Comments

No Known Activations