INDEX

Explanations

articles, prepositions and short words starting with letters "i" or "a".

oai_token-act-pair · gemini-2.0-flash

Specific details and terms

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ErrUnexpectedEOF

-0.59

'][]

-0.59

 lenker

-0.56

IsMutable

-0.55

 nahilalakip

-0.54

Попис

-0.52

CopyWith

-0.52

Datuak

-0.50

 صوتيه

-0.48

MemoryWarning

-0.47

POSITIVE LOGITS

Efq

0.77

 pleaſure

0.73

enderror

0.68

 fhew

0.66

 neceff

0.63

 Monfieur

0.62

OOTDTY

0.62

 avoient

0.62

 varandra

0.61

 mourut

0.61

Activations Density 0.210%

articles, prepositions and short words starting with letters "i" or "a".

Specific details and terms

No Comments

No Known Activations