INDEX

Explanations

references to neural network operations and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

sscanf

-0.44

(\%)

-0.44

 maximum

-0.41

autant

-0.40

copg

-0.40

سام

-0.40

leih

-0.40

uttore

-0.39

 Tenggara

-0.39

omena

-0.39

POSITIVE LOGITS

 חיצוניים

0.81

ImageContext

0.80

 estekak

0.75

 linkovi

0.74

лтемелер

0.73

 kaarangay

0.72

modelBuilder

0.71

featureID

0.70

verifyException

0.66

 weights

0.66

Activations Density 0.437%

references to neural network operations and their effects

No Comments

No Known Activations