INDEX

Explanations

phrases indicating alternative names or designations for entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

tagHelperRunner

-0.90

 ProtoMessage

-0.90

yntaxException

-0.90

archiviato

-0.86

InputBorder

-0.86

 незавершена

-0.85

+#+#

-0.85

OGND

-0.80

 <=",

-0.79

MLLoader

-0.77

POSITIVE LOGITS

aka

0.82

AKA

0.69

 called

0.69

 appelé

0.66

 называ

0.64

aka

0.64

 popularly

0.64

called

0.63

 alias

0.62

 known

0.62

Activations Density 0.369%

phrases indicating alternative names or designations for entities

No Comments

No Known Activations