INDEX

Explanations

terms related to legislative processes and recommendations

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

preceding time-related events

np_acts-logits-general · gemini-2.0-flash

upcoming announcements and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

previous

-0.58

 previous

-0.57

 Previous

-0.55

Previous

-0.53

 blevet

-0.52

 PREVIOUS

-0.50

 бы

-0.49

 précédentes

-0.48

 précédents

-0.47

 olmuş

-0.47

POSITIVE LOGITS

 tomorrow

2.59

 soon

2.10

tomorrow

2.10

 prochain

2.02

 next

2.00

 demain

1.98

 upcoming

1.96

 amanhã

1.85

 komende

1.82

soon

1.81

Activations Density 0.782%

terms related to legislative processes and recommendations

preceding time-related events

upcoming announcements and outcomes

No Comments

No Known Activations