INDEX

Explanations

positive evaluations of experiences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Punctuation marks in text

np_acts-logits-general · gemini-2.0-flash

end of sentence descriptors

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ScopeManager

-0.68

 AssemblyCompany

-0.61

 AppCompatTheme

-0.58

ษัท

-0.57

 चीज़ों

-0.56

 isSelected

-0.55

Collectors

-0.55

-0.54

crites

-0.53

urende

-0.53

POSITIVE LOGITS

 staff

0.90

 Staff

0.76

staff

0.73

Staff

0.73

 personale

0.65

Friendly

0.64

:✨

0.64

Helpful

0.63

 Friendly

0.62

Everything

0.62

Activations Density 0.043%

positive evaluations of experiences

Punctuation marks in text

end of sentence descriptors

No Comments

No Known Activations