INDEX

Explanations

words related to website usability and legal requirements

oai_token-act-pair · gemini-2.0-flash

terms related to accessibility and disability

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

accessibility

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

ILayout

-0.55

GeneratedMessage

-0.49

afficheront

-0.49

RTEE

-0.47

 delin

-0.46

 الحره

-0.46

WithIOException

-0.45

 bross

-0.43

lossians

-0.43

::~

-0.43

POSITIVE LOGITS

 accessibility

1.70

 accessible

1.62

 Accessible

1.52

 Accessibility

1.50

accessible

1.43

 disabled

1.39

Accessible

1.38

Accessibility

1.33

accessibility

1.30

 disability

1.30

Activations Density 1.721%

words related to website usability and legal requirements

terms related to accessibility and disability

accessibility

No Comments

No Known Activations