INDEX

Explanations

the word "sit" or "sat" and words that are near it

oai_token-act-pair · gemini-2.0-flash

sit

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

parsedMessage

-0.84

ColumnHeaders

-0.76

 estekak

-0.73

writeFieldEnd

-0.71

 Италијани

-0.70

modelBuilder

-0.69

:✨

-0.69

 مشين

-0.68

BagConstraints

-0.66

 estimés

-0.66

POSITIVE LOGITS

 down

0.56

 still

0.51

god

0.46

 there

0.45

imah

0.43

telle

0.43

WriteTagHelper

0.42

hatta

0.41

 tslint

0.38

hon

0.38

Activations Density 0.403%

the word "sit" or "sat" and words that are near it

sit

No Comments

No Known Activations