INDEX

Explanations

references to a specific item or title

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

OGND

-0.68

 Völ

-0.62

ArrowToggle

-0.62

 Forman

-0.62

RTHOOK

-0.62

XmlEnum

-0.61

 Berger

-0.60

}();

-0.60

FileDescriptor

-0.60

StructEnd

-0.60

POSITIVE LOGITS

enderror

0.78

this

0.77

存于互联网档案馆

0.70

 demurrer

0.65

 متعلقه

0.62

 aceton

0.61

ligators

0.59

 nonatomic

0.57

 rhetor

0.57

 tandis

0.56

Activations Density 0.003%

references to a specific item or title

No Comments

No Known Activations