INDEX

Explanations

references to magnetism and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Audiodateien

-0.67

Читайте

-0.61

verwijspagina

-0.59

rawDesc

-0.58

ContentAsync

-0.56

Rhestr

-0.55

KommentareTeilen

-0.54

tagHelperRunner

-0.53

 članak

-0.53

LayoutPanel

-0.52

POSITIVE LOGITS

BeginContext

0.65

pie

0.59

 kasarigan

0.59

الحياه

0.58

 propOrder

0.56

aarrggbb

0.56

Slf

0.54

pied

0.54

stripe

0.53

 Carta

0.52

Activations Density 0.235%

references to magnetism and related terms

No Comments

No Known Activations