INDEX

Explanations

references to organizational structures or frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

/\.

-0.68

 autorytatywna

-0.63

 AssemblyProduct

-0.60

ReusableCell

-0.56

OGND

-0.56

 للمعارف

-0.56

 BoxFit

-0.55

artifactId

-0.55

asgi

-0.54

 coar

-0.54

POSITIVE LOGITS

 computerized

1.31

 automated

1.19

 system

1.17

 computer

1.17

 systems

1.17

 software

1.12

 electronic

1.09

 database

1.07

 computers

1.06

 automate

1.05

Activations Density 0.419%

references to organizational structures or frameworks

No Comments

No Known Activations