INDEX

Explanations

references to programming or code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

AndEndTag

-0.44

 ſtand

-0.44

 ſta

-0.41

makeConstraints

-0.40

BeginInit

-0.39

 kväll

-0.39

ISupport

-0.38

 verkla

-0.37

之間

-0.36

Vict

-0.36

POSITIVE LOGITS

nestjs

0.44

Diweddarwch

0.42

 EconPapers

0.42

PyExc

0.42

angular

0.41

stridium

0.41

WebElementEntity

0.41

 يتيمه

0.40

oplayer

0.40

 '\\;'

0.39

Activations Density 0.313%

references to programming or code snippets

No Comments

No Known Activations