INDEX

Explanations

references to user-related activities or functions within a coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

subsection

-0.88

 Kearney

-0.70

UNE

-0.68

 contextLoads

-0.65

 Leaderboard

-0.63

CNA

-0.63

 Nema

-0.62

SequentialGroup

-0.61

 Heinemann

-0.61

osé

-0.60

POSITIVE LOGITS

subsubsection

1.70

Pyx

0.71

 entanto

0.68

indexPath

0.67

ksom

0.66

rungsseite

0.66

AndEndTag

0.66

ânica

0.64

 Marquez

0.63

 تانيه

0.62

Activations Density 0.004%

references to user-related activities or functions within a coding context

No Comments

No Known Activations