INDEX

Explanations

references to protocols and their versions in technical documents

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-1.09

 Theſe

-0.90

 becauſe

-0.81

 renunciation

-0.77

 AIAA

-0.76

dibles

-0.76

 Monfieur

-0.76

 Jefus

-0.74

 Mastery

-0.73

Eſ

-0.73

POSITIVE LOGITS

 protocols

1.55

 protocol

1.54

 Protocol

1.43

Protocol

1.28

 PROTOCOL

1.24

 Protocols

1.22

protocol

1.20

Protocols

1.13

protocols

1.04

 protocolo

1.02

Activations Density 0.012%

references to protocols and their versions in technical documents

No Comments

No Known Activations