INDEX

Explanations

cleaning actions in various contexts

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

Sized

-0.49

ően

-0.45

complexContent

-0.42

odle

-0.42

 tepung

-0.42

__(/*!

-0.42

VERTIS

-0.42

 настоя

-0.41

Datuak

-0.41

 getParent

-0.39

POSITIVE LOGITS

 surfaces

1.15

 floors

1.03

 areas

0.99

 hallways

0.95

 interiors

0.93

 walls

0.89

 roads

0.88

 sidewalks

0.87

surfaces

0.87

 walkways

0.86

Activations Density 0.259%

cleaning actions in various contexts

No Comments

No Known Activations