INDEX

Explanations

Java annotations for entity identification in a data structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IContainer

-1.04

/*

-1.00

findpost

-0.99

/*---

-0.99

Datuak

-0.95

="#"><

-0.95

~*~

-0.95

WireFormatLite

-0.90

Tikang

-0.89

 Krav

-0.87

POSITIVE LOGITS

ity

1.04

 Rina

0.76

Ceb

0.76

 Carla

0.74

 Charlemagne

0.72

 Edson

0.72

Carla

0.71

 СО

0.70

 Colbert

0.70

 Hanne

0.70

Activations Density 0.572%

Java annotations for entity identification in a data structure

No Comments

No Known Activations