INDEX

Explanations

proper nouns related to specific individuals and organizations, particularly within the context of sports and academia

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

𝘪

-0.71

 Hawthorn

-0.68

 Shelly

-0.68

віт

-0.67

 Kays

-0.66

 Castor

-0.66

Adri

-0.66

ὶ

-0.65

𝘬

-0.64

 bouteille

-0.64

POSITIVE LOGITS

providedIn

1.16

Cattle

0.96

Beef

0.93

 cattle

0.92

 Cattle

0.92

GEBURTSDATUM

0.91

 Beef

0.89

 Cows

0.88

 beef

0.86

 kasarigan

0.85

Activations Density 3.414%

proper nouns related to specific individuals and organizations, particularly within the context of sports and academia

No Comments

No Known Activations