INDEX

Explanations

legal terminology and references to court cases

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

followed by "in" or "during"

np_acts-logits-general · gemini-2.0-flash

in a context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

पया

-0.73

makeConstraints

-0.71

 ModelExpression

-0.70

enumii

-0.67

AccessorTable

-0.66

ReusableCell

-0.62

URLException

-0.61

Portail

-0.60

Tikang

-0.59

 createState

-0.58

POSITIVE LOGITS

 parlando

0.60

lässlich

0.58

:✨

0.56

advert

0.56

IVIA

0.55

 reacting

0.55

Lors

0.54

livre

0.53

 lors

0.53

 context

0.53

Activations Density 0.586%

legal terminology and references to court cases

followed by "in" or "during"

in a context

No Comments

No Known Activations