INDEX

Explanations

technical terms and concepts related to programming, mathematics, and medical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

✭✭

-0.60

 frattempo

-0.59

antMatchers

-0.56

GIVEREF

-0.54

 ferons

-0.51

uelos

-0.50

 dichiarato

-0.49

Bend

-0.49

 bénévol

-0.48

 CURLOPT

-0.47

POSITIVE LOGITS

 indexes

0.72

Solución

0.67

 Système

0.67

 indexed

0.65

 viewDidLoad

0.65

webElementXpaths

0.64

 indices

0.64

 index

0.63

 Bump

0.63

 IndexError

0.63

Activations Density 2.883%

technical terms and concepts related to programming, mathematics, and medical data

No Comments

No Known Activations