INDEX

Explanations

references to academic conferences and proceedings in the field of machine learning and artificial intelligence

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

Conference proceedings

np_acts-logits-general · gemini-2.0-flash

international conference proceedings

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 оригіналу

-0.59

üstet

-0.55

 consultato

-0.54

 برانيه

-0.51

原始内容存档于

-0.49

 seeing

-0.47

 Zwiebel

-0.47

ocracy

-0.47

 CreateTagHelper

-0.47

帖最后由

-0.47

POSITIVE LOGITS

 annual

0.67

 Annual

0.67

 international

0.66

 International

0.63

Annual

0.62

annual

0.62

international

0.59

 Joint

0.55

 annuel

0.55

International

0.55

Activations Density 0.130%

references to academic conferences and proceedings in the field of machine learning and artificial intelligence

Conference proceedings

international conference proceedings

No Comments

No Known Activations