INDEX

Explanations

technical terms related to alloys and metalworking

oai_token-act-pair · gemini-2.0-flash

technical product names or code-related terms

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

Metallurgy/manufacturing

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

 BoxFit

-0.66

 onPostExecute

-0.59

 onAnimation

-0.56

SequentialGroup

-0.56

anada

-0.55

RefNanny

-0.55

tuta

-0.52

सन्दर्भ

-0.51

 hell

-0.50

Bof

-0.50

POSITIVE LOGITS

 Wikimedijinoj

0.56

PreInfinity

0.53

HtmlAttribute

0.52

хьтан

0.51

SourceChecksum

0.49

base

0.48

 createSlice

0.48

 AssemblyProduct

0.47

 utafitiHapana

0.47

RotationOrder

0.46

Activations Density 2.089%

technical terms related to alloys and metalworking

technical product names or code-related terms

Metallurgy/manufacturing

No Comments

No Known Activations