INDEX

Explanations

words with negative connotations relating to quality, and to a lesser extent, positive ones

oai_token-act-pair · gemini-2.0-flash

attributes related to quality

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

poor

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

onAttach

-0.56

 similaires

-0.50

ANGO

-0.50

тьяна

-0.49

 arrivato

-0.48

šanai

-0.47

mybatisplus

-0.47

 pleins

-0.47

letti

-0.47

 ragione

-0.46

POSITIVE LOGITS

 performance

0.93

 acoustics

0.92

 quality

0.90

 visibility

0.89

 readability

0.88

 usability

0.84

 cleanliness

0.81

 efficiency

0.80

 reliability

0.80

 productivity

0.79

Activations Density 5.307%

words with negative connotations relating to quality, and to a lesser extent, positive ones

attributes related to quality

poor

No Comments

No Known Activations