INDEX

Explanations

references to the name "Bur" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

){

-0.73

principalTable

-0.70

 Avan

-0.68

❯

-0.68

/*---

-0.66

++

-0.66

__':

-0.64

nesota

-0.64

"):

-0.64

脚注の使い方

-0.61

POSITIVE LOGITS

Bur

3.27

Bur

3.20

bur

3.01

bur

2.93

BUR

2.62

BUR

2.48

 Burr

1.71

 Burk

1.69

 Burrell

1.54

 Бур

1.53

Activations Density 0.064%

references to the name "Bur" in various contexts

No Comments

No Known Activations