INDEX

Explanations

code snippets, web elements (file, tables etc), algorithms, features and other computer/programming terminology

oai_token-act-pair · gemini-2.0-flash

technical terms related to programming or API elements

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

element

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

+#+

-0.66

 propOrder

-0.61

AxisAlignment

-0.59

 ProtoMessage

-0.57

CppCodeGen

-0.57

 ويكيميديا

-0.55

jooq

-0.54

libft

-0.53

 <<<<<<<<<<<<<<

-0.53

 énergé

-0.52

POSITIVE LOGITS

httphttps

0.52

 intptr

0.51

fml

0.48

BufferException

0.48

ndrome

0.48

 Référence

0.46

 محفوظة

0.45

reference

0.45

 DbType

0.44

είτε

0.42

Activations Density 5.468%

code snippets, web elements (file, tables etc), algorithms, features and other computer/programming terminology

technical terms related to programming or API elements

element

No Comments

No Known Activations