INDEX

Explanations

references to experiences or evaluations of individuals and their actions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 surrounded

-0.52

 angekommen

-0.47

intios

-0.44

 Wiktionnaire

-0.42

 égard

-0.42

Derbyniad

-0.41

DetailComponent

-0.40

nasium

-0.40

mulos

-0.40

 naturen

-0.39

POSITIVE LOGITS

 lenient

0.79

 ModelExpression

0.78

 generous

0.78

/**

0.76

 unhelpful

0.75

 gracious

0.72

cooperative

0.71

 amables

0.71

 courteous

0.71

TestingModule

0.70

Activations Density 0.324%

references to experiences or evaluations of individuals and their actions

No Comments

No Known Activations