INDEX

Explanations

generally significant names and terms related to a specific academic or scientific context

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

 Sasha

-0.76

 Adams

-0.72

 kaynağından

-0.70

HashCode

-0.70

ヒル

-0.70

 Sach

-0.70

 Marlins

-0.69

Paola

-0.68

 Gerr

-0.67

WebServlet

-0.67

POSITIVE LOGITS

 Beres

0.98

Rha

0.92

httphttps

0.89

 Winfrey

0.87

 portuguesa

0.83

CTP

0.83

 tawny

0.82

 CreateTagHelper

0.82

 Metropolitana

0.80

 ChatGPT

0.80

Activations Density 1.836%

generally significant names and terms related to a specific academic or scientific context

No Comments

No Known Activations