INDEX

Explanations

structured references and definitions related to programming libraries or resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

########.

-0.97

Hauptartikel

-0.81

expandindo

-0.78

 متعلقه

-0.77

͡

-0.77

 "..\..\

-0.75

rophoresis

-0.74

CodeAttribute

-0.73

MTI

-0.72

 HasFactory

-0.71

POSITIVE LOGITS

com

1.62

COM

1.50

Com

1.42

Com

1.32

COM

1.31

com

1.24

coms

1.06

 COMM

0.99

 Comstock

0.97

KOM

0.96

Activations Density 0.052%

structured references and definitions related to programming libraries or resources

No Comments

No Known Activations