INDEX

Explanations

code snippets and lists of items separated by commas

oai_token-act-pair · gemini-2.0-flash

unusual characters or foreign words

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

Calculations/Errors

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

parsedMessage

-0.60

AutoScaleMode

-0.59

 propOrder

-0.56

paksa

-0.54

ngdoc

-0.52

GeneratedMessage

-0.50

 autorytatywna

-0.49

eleste

-0.49

det

-0.49

timewa

-0.48

POSITIVE LOGITS

 morire

0.65

NUMX

0.63

 Moslem

0.60

MOP

0.60

 Shakspeare

0.59

 itſelf

0.58

endgroup

0.57

adays

0.57

 vierge

0.56

 umana

0.55

Activations Density 3.434%

code snippets and lists of items separated by commas

unusual characters or foreign words

Calculations/Errors

No Comments

No Known Activations