INDEX

Explanations

references to convolutional neural networks (CNNs) and their capabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

tinyos

-0.56

 STEWART

-0.55

roek

-0.54

 cowardice

-0.53

findpost

-0.52

ThroughAttribute

-0.52

 morire

-0.51

 AssemblyVersion

-0.50

 Boyce

-0.49

 Cataloging

-0.49

POSITIVE LOGITS

 training

1.14

 trained

1.10

 neural

1.00

 train

0.93

Training

0.91

 Neural

0.90

 Training

0.90

trained

0.89

train

0.88

training

0.86

Activations Density 1.769%

references to convolutional neural networks (CNNs) and their capabilities

No Comments

No Known Activations