INDEX

Explanations

references to notable individuals and locations associated with cultural contributions or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ագրություններ

-0.75

 nonUne

-0.65

 Jefus

-0.62

 deſt

-0.59

 ſever

-0.58

 tramonto

-0.55

 CreateTagHelper

-0.55

 faſt

-0.55

 himſelf

-0.55

 kasarigan

-0.55

POSITIVE LOGITS

 pioneer

0.41

subset

0.40

 Dispens

0.39

stuk

0.38

ned

0.37

 sticking

0.37

 diver

0.37

ASP

0.36

lev

0.36

 fucking

0.36

Activations Density 1.944%

references to notable individuals and locations associated with cultural contributions or significance

No Comments

No Known Activations