INDEX

Explanations

terms and concepts related to machine learning and artificial intelligence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

__(/*!

-0.68

◄

-0.60

 שוליים

-0.54

mergeFrom

-0.52

hips

-0.52

endő

-0.51

نامه

-0.49

 useParams

-0.49

-0.48

האם

-0.48

POSITIVE LOGITS

 learning

0.83

learning

0.74

 Learning

0.73

 LEARNING

0.70

gun

0.69

 washable

0.68

Learning

0.67

 Washable

0.66

gun

0.64

 guns

0.61

Activations Density 0.227%

terms and concepts related to machine learning and artificial intelligence

No Comments

No Known Activations