INDEX

Explanations

technical terms and code constructs related to programming and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

FORMANCE

-0.57

slo

-0.46

WART

-0.45

Hal

-0.45

STRA

-0.44

né

-0.43

Ser

-0.43

Parab

-0.43

orant

-0.43

ATTACH

-0.43

POSITIVE LOGITS

GEBURTSDATUM

1.15

 архивлан

0.88

Personensuche

0.82

GenerationType

0.81

Efq

0.79

Jeografia

0.77

WithIOException

0.76

 itſelf

0.76

uxxxx

0.76

 ویکی‌پدیا

0.76

Activations Density 3.155%

technical terms and code constructs related to programming and specifications

No Comments

No Known Activations