INDEX

Explanations

the word "To" or "TO"

oai_token-act-pair · gemini-2.0-flash

say [uppercase word]

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

+=

-0.46

Jedis

-0.42

need

-0.40

KeySpec

-0.40

 Very

-0.40

Need

-0.40

emon

-0.39

-=

-0.38

 Need

-0.38

お

-0.38

POSITIVE LOGITS

 Exacts

0.88

 Anſ

0.81

 myſelf

0.80

 becauſe

0.80

 Houſe

0.76

 chofe

0.76

 purpoſe

0.75

 houſe

0.73

 greateſt

0.73

 Theſe

0.71

Activations Density 0.346%

the word "To" or "TO"

say [uppercase word]

No Comments

No Known Activations