INDEX

Explanations

terms related to insurance and legal concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

-0.41

 Gedanken

-0.39

ⓧ

-0.39

 Monteiro

-0.38

acuzzi

-0.37

Décès

-0.36

beqa

-0.36

ollectionView

-0.36

terung

-0.36

 ujednoznacz

-0.35

POSITIVE LOGITS

Ins

3.78

Ins

3.67

ins

3.56

ins

3.23

INS

2.81

INS

2.75

 insu

1.97

 insulator

1.76

 insulating

1.74

 insulators

1.73

Activations Density 0.166%

terms related to insurance and legal concepts

No Comments

No Known Activations