INDEX

Explanations

terms related to "ultra" and high-performance attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Santis

-0.79

rillation

-0.71

MessageOf

-0.70

providedIn

-0.69

Personendaten

-0.68

 Pisa

-0.68

bellar

-0.68

knex

-0.67

AnimationsModule

-0.67

JspWriter

-0.67

POSITIVE LOGITS

 Ultra

3.13

 ultra

2.97

Ultra

2.85

ultra

2.75

 ULTRA

2.67

 ultras

2.21

ult

1.92

 ультра

1.82

 ultraviolet

1.33

超

1.30

Activations Density 0.073%

terms related to "ultra" and high-performance attributes

No Comments

No Known Activations