INDEX

Explanations

mentions of individuals and their affiliations or positions, particularly in contexts related to governance or legal matters

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

after commas

np_acts-logits-general · gemini-2.0-flash

titles, roles, or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 bestehende

-0.52

toarele

-0.51

SequentialGroup

-0.49

 bestehenden

-0.49

 Slovensku

-0.49

 gratuites

-0.48

€.

-0.48

 persoane

-0.48

にかけて

-0.48

GRANTED

-0.46

POSITIVE LOGITS

 owner

0.91

who

0.86

 alias

0.78

 founder

0.75

owner

0.73

 formerly

0.73

son

0.73

aka

0.72

 better

0.70

 nephew

0.69

Activations Density 0.173%

mentions of individuals and their affiliations or positions, particularly in contexts related to governance or legal matters

after commas

titles, roles, or relationships

No Comments

No Known Activations