INDEX

Explanations

references to various acronyms and terms related to biological and computational processes

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

Scénario

-0.71

GOTREF

-0.69

asymp

-0.69

SceneManagement

-0.67

chaffen

-0.65

Condol

-0.65

 Shanti

-0.65

verwijspagina

-0.64

 Leonid

-0.64

 extraordin

-0.64

POSITIVE LOGITS

.*")]

0.92

Ivoire

0.90

 Ives

0.81

 iArr

0.78

 getId

0.75

 Isaacs

0.74

Ire

0.74

Ike

0.72

Ips

0.71

 Irving

0.71

Activations Density 0.738%

references to various acronyms and terms related to biological and computational processes

No Comments

No Known Activations