INDEX

Explanations

terms related to legal processes and their implications

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

describing a state or action

np_acts-logits-general · gemini-2.0-flash

status conditions and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 للمعارف

-0.66

 تضيفلها

-0.56

-0.55

 betweenstory

-0.54

 Normdatei

-0.50

chränk

-0.49

ValueStyle

-0.48

లాలు

-0.48

ViewFeatures

-0.47

middels

-0.45

POSITIVE LOGITS

 propOrder

0.46

by

0.42

priority

0.37

 priority

0.37

BackStack

0.36

cesis

0.36

 Bersama

0.35

 under

0.35

rawValue

0.35

 Grosvenor

0.35

Activations Density 0.766%

terms related to legal processes and their implications

describing a state or action

status conditions and outcomes

No Comments

No Known Activations