INDEX

Explanations

specific deep learning architecture components and their attributes

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

 propOrder

-0.55

 ostavi

-0.52

 nahilalakip

-0.52

WebElementEntity

-0.52

tanleria

-0.50

Ecotoxicity

-0.49

 Rang

-0.49

 AssemblyCulture

-0.48

rophoto

-0.48

igslist

-0.48

POSITIVE LOGITS

 conv

0.81

Conv

0.79

 Conv

0.78

 pooling

0.74

conv

0.74

 convolutional

0.68

 convolution

0.67

 Pool

0.67

 pool

0.66

 layer

0.66

Activations Density 0.216%

specific deep learning architecture components and their attributes

No Comments

No Known Activations