INDEX

Explanations

statements about not knowing and learning

oai_token-act-pair · gemini-2.0-flash

knowledge and certainty

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

know

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

 للاسماء

-0.75

endphp

-0.65

NewUrlParser

-0.65

 ويكيپيديا

-0.61

 vulgaires

-0.57

 paroisse

-0.57

myModal

-0.57

Scooter

-0.56

assination

-0.56

 ویکی‌پدیا

-0.55

POSITIVE LOGITS

for

0.61

Tikang

0.49

 Loves

0.47

 Style

0.47

Style

0.46

ContentAsync

0.46

tagHelper

0.43

velo

0.43

 cosa

0.41

hoben

0.41

Activations Density 2.022%

statements about not knowing and learning

knowledge and certainty

know

No Comments

No Known Activations