INDEX

Explanations

terms related to legal definitions and medical guidelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 surla

-0.44

 nakalista

-0.40

BN

-0.34

LG

-0.34

Els

-0.33

KEYCODE

-0.32

PE

-0.32

teig

-0.32

PM

-0.32

TG

-0.32

POSITIVE LOGITS

StructEnd

0.62

ChildScrollView

0.57

ConstraintMaker

0.53

 Infór

0.53

nsito

0.51

 transférez

0.51

kmäler

0.50

 ſind

0.49

erialize

0.48

astify

0.48

Activations Density 2.407%

terms related to legal definitions and medical guidelines

No Comments

No Known Activations