INDEX

Explanations

topics related to language processing and language deficits in children

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.37.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Numerade

-0.51

Gweler

-0.49

GEBURTS

-0.45

 فريبيس

-0.43

IntoConstraints

-0.42

 defaultstate

-0.42

 autorytatywna

-0.41

 physics

-0.41

Билгалдахарш

-0.41

Physics

-0.40

POSITIVE LOGITS

 recall

0.53

 sight

0.52

 externi

0.47

IContainer

0.46

 Recall

0.46

 Sight

0.45

Flu

0.45

 retrieval

0.44

 Concepts

0.43

 Erişim

0.43

Activations Density 0.252%

topics related to language processing and language deficits in children

No Known Activations