INDEX

Explanations

words related to legal terms and processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 NSCoder

-0.56

ValueStyle

-0.45

 defaultstate

-0.42

CppCodeGen

-0.41

 doPost

-0.40

 Italijani

-0.38

 continúas

-0.37

 assoluto

-0.36

RepeatedField

-0.36

TagMode

-0.36

POSITIVE LOGITS

 ramps

0.66

 ramp

0.64

Ram

0.63

 Ramp

0.61

Ramp

0.57

Ram

0.57

Vibr

0.57

resize

0.56

 Vibr

0.56

GEBURTSDATUM

0.55

Activations Density 0.578%

words related to legal terms and processes

No Comments

No Known Activations