INDEX

Explanations

technical descriptions of inverters and sentiment towards a production.

oai_token-act-pair · gemini-2.0-flash

technical terms related to inverter applications

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

film or code

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

}{*}{

-0.48

 Morelos

-0.48

 hObject

-0.47

 hial

-0.47

 Preferencias

-0.47

)}_{

-0.46

nosi

-0.46

 Furcht

-0.45

 autón

-0.45

FLOR

-0.44

POSITIVE LOGITS

migrationBuilder

0.79

ViewFeatures

0.68

ագրություններ

0.68

prefixer

0.66

 صوتيه

0.63

tanleria

0.56

 AdapterView

0.56

igshid

0.54

NetworkInfo

0.54

apunov

0.52

Activations Density 0.297%

technical descriptions of inverters and sentiment towards a production.

technical terms related to inverter applications

film or code

No Comments

No Known Activations